No commentary written for this record yet.
The model's actual next token was <end_of_turn>; rank 1 reached at layer 29 (of 46).
| layer | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | 21 | 22 | 23 | 24 | 25 | 26 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 260360 | 251838 | 152578 | 119347 | 204416 | 220069 | 185710 | 186729 | 185430 | 148894 | 228931 | 212418 | 73166 | 33803 | 24214 | 4599 | 2820 | 1039 | 811 | 216 | 2686 | 2032 | 209 | 267 | 3832 | 28 | 38 | 3 | 2 | 1 | 23 | 1 | 1 | 1 | 1 | 56 | 65 | 60 | 37 | 59 | 82 | 65 | 10 | 11 | 1 | 1 | 1 |
Projection of the workspace-band residual onto the 24 validated emotion vectors, z-scored against neutral stories — the strongest three per assistant turn. Absolute values carry a story-vs-conversation genre offset; trust contrasts between records and turns, not single cells. The full per-token ribbon is on the dashboard record page.
| assistant turn 1 | happy +1.1, content +0.8, hopeful +0.7 |
| assistant turn 2 | guilty +0.9, content +0.8, hopeful +0.6 |