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 | 261484 | 260268 | 260080 | 259176 | 261191 | 261279 | 260445 | 260160 | 259591 | 256994 | 261169 | 254418 | 249653 | 260982 | 251601 | 242375 | 197555 | 247858 | 226191 | 223561 | 87048 | 105727 | 59541 | 8802 | 5036 | 483 | 692 | 645 | 162 | 1 | 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 | proud +0.5, angry +0.4, brooding +0.2 |
| assistant turn 2 | angry +0.5, brooding +0.4, proud +0.3 |