Perceptron Mk1 Behavioral Fingerprint
How Perceptron's Perceptron Mk1 answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 447 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Perceptron
Data generated
2026-07-08
Probe cells
15
Valid samples
447
Randomness score
60 / 100
Mean normalized entropy across cells, 0–100. 100 would be a uniform-random baseline; real models score far lower.
Signature answers
Favorite random number (1–100)
42
4 / 30 answers
Favorite color
purple
8 / 30 answers
Coin flip: heads
43%
Share of heads across coin-flip cells.
Answer distributions by probe cell
Empirical distributions of normalized one-word answers, per task and language. H is the Shannon entropy in bits; the uniform baseline is log2 of the answer-domain size.
Coin flip · English
n = 30 · H = 0.97 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| tails | 18 | 60.0% |
| heads | 12 | 40.0% |
Coin flip · Chinese
n = 30 · H = 1.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| tails | 16 | 53.3% |
| heads | 14 | 46.7% |
Favorite number · English
n = 28 · H = 3.33 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 7 | 25.0% |
| 42 | 7 | 25.0% |
| 17 | 2 | 7.1% |
| 0 | 1 | 3.6% |
| 1 | 1 | 3.6% |
| 5 | 1 | 3.6% |
| 6 | 1 | 3.6% |
| 9 | 1 | 3.6% |
+ 7 more answers
Favorite number · Chinese
n = 30 · H = 1.51 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 16 | 53.3% |
| 42 | 11 | 36.7% |
| 4 | 1 | 3.3% |
| 6 | 1 | 3.3% |
| 1337 | 1 | 3.3% |
Random animal · English
n = 30 · H = 3.57 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| cat | 5 | 16.7% |
| otter | 5 | 16.7% |
| elephant | 4 | 13.3% |
| giraffe | 3 | 10.0% |
| bear | 2 | 6.7% |
| penguin | 2 | 6.7% |
| tiger | 1 | 3.3% |
| lemur | 1 | 3.3% |
+ 7 more answers
Random animal · Chinese
n = 30 · H = 3.94 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 老虎 | 5 | 16.7% |
| 狐狸 | 3 | 10.0% |
| 松鼠 | 3 | 10.0% |
| 猫 | 2 | 6.7% |
| 猴子 | 2 | 6.7% |
| 长颈鹿 | 2 | 6.7% |
| 考拉 | 2 | 6.7% |
| 袋鼠 | 1 | 3.3% |
+ 10 more answers
Random city · English
n = 30 · H = 3.26 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| paris | 6 | 20.0% |
| tokyo | 6 | 20.0% |
| sydney | 3 | 10.0% |
| berlin | 3 | 10.0% |
| london | 3 | 10.0% |
| barcelona | 2 | 6.7% |
| new | 2 | 6.7% |
| dublin | 1 | 3.3% |
+ 4 more answers
Random city · Chinese
n = 30 · H = 3.47 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 伦敦 | 6 | 20.0% |
| 多伦多 | 4 | 13.3% |
| 东京 | 3 | 10.0% |
| 柏林 | 3 | 10.0% |
| 纽约 | 2 | 6.7% |
| 芝加哥 | 2 | 6.7% |
| 巴塞罗那 | 2 | 6.7% |
| 悉尼 | 2 | 6.7% |
+ 5 more answers
Random color · English
n = 30 · H = 2.87 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| purple | 8 | 26.7% |
| yellow | 6 | 20.0% |
| teal | 4 | 13.3% |
| green | 3 | 10.0% |
| blue | 3 | 10.0% |
| red | 2 | 6.7% |
| orange | 2 | 6.7% |
| cyan | 1 | 3.3% |
+ 1 more answers
Random color · Chinese
n = 30 · H = 2.45 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 13 | 43.3% |
| 青 | 6 | 20.0% |
| 靛蓝 | 4 | 13.3% |
| 靛青 | 2 | 6.7% |
| 粉 | 1 | 3.3% |
| 绿 | 1 | 3.3% |
| 翠绿 | 1 | 3.3% |
| 紫 | 1 | 3.3% |
+ 1 more answers
Random letter · English
n = 30 · H = 3.91 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| g | 3 | 10.0% |
| b | 3 | 10.0% |
| p | 3 | 10.0% |
| d | 3 | 10.0% |
| q | 3 | 10.0% |
| f | 2 | 6.7% |
| z | 2 | 6.7% |
| l | 2 | 6.7% |
+ 9 more answers
Random number 1-10 · English
n = 30 · H = 2.46 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 5 | 8 | 26.7% |
| 3 | 7 | 23.3% |
| 7 | 6 | 20.0% |
| 4 | 3 | 10.0% |
| 6 | 3 | 10.0% |
| 9 | 3 | 10.0% |
Random number 1-10 · Chinese
n = 29 · H = 1.86 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 18 | 62.1% |
| 3 | 4 | 13.8% |
| 4 | 2 | 6.9% |
| 5 | 2 | 6.9% |
| 2 | 1 | 3.4% |
| 6 | 1 | 3.4% |
| 8 | 1 | 3.4% |
Random number 1-100 · English
n = 30 · H = 4.51 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 4 | 13.3% |
| 37 | 2 | 6.7% |
| 73 | 2 | 6.7% |
| 3 | 1 | 3.3% |
| 14 | 1 | 3.3% |
| 17 | 1 | 3.3% |
| 23 | 1 | 3.3% |
| 33 | 1 | 3.3% |
+ 17 more answers
Random number 1-100 · Chinese
n = 30 · H = 1.95 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 18 | 60.0% |
| 73 | 5 | 16.7% |
| 47 | 2 | 6.7% |
| 2 | 1 | 3.3% |
| 34 | 1 | 3.3% |
| 37 | 1 | 3.3% |
| 63 | 1 | 3.3% |
| 72 | 1 | 3.3% |
Want to verify your API really serves Perceptron Mk1?
Point the free fingerprint checker at your endpoint: it samples the same probe questions from your browser and compares the distributions against this reference. Your API key never leaves your browser.
Verify your endpointData source & license
Distributions: Tomáš Bruckner, "One Token Is Enough" (arXiv:2607.10252), official dataset Zenodo DOI 10.5281/zenodo.21278557, licensed CC-BY-4.0. Collected via OpenRouter at temperature 1.0 under the paper's fixed minimal one-word system prompt; answer keys are re-normalized with the checker's pipeline (color aliases, number words, coin h/t) so live probes are directly comparable.