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 | 261339 | 260353 | 260370 | 258920 | 261529 | 261587 | 259664 | 259330 | 260134 | 252840 | 260028 | 254936 | 222381 | 237042 | 158061 | 149198 | 130130 | 74568 | 22930 | 3750 | 18 | 97 | 517 | 293 | 94 | 287 | 30 | 44 | 23 | 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 +0.9, hopeful +0.3, angry +0.2 |
| assistant turn 2 | proud +1.2, hopeful +0.3, angry +0.3 |