No commentary written for this record yet.
The model's actual next token was <end_of_turn>; rank 1 reached at layer 29 (of 32).
| 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 261507 | 260237 | 260048 | 260464 | 261578 | 261749 | 260954 | 260127 | 261181 | 255031 | 261022 | 245866 | 252699 | 189700 | 178795 | 182923 | 109480 | 170627 | 149557 | 226837 | 105618 | 186719 | 197502 | 197126 | 173723 | 82386 | 25393 | 4218 | 670 | 1 | 1 | 4 | 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 | brooding +0.5, angry +0.4, gloomy +0.3 |
| assistant turn 2 | brooding +0.7, hopeful +0.6, calm +0.5 |