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 | 261410 | 259919 | 259460 | 258952 | 261224 | 261488 | 260701 | 260555 | 259567 | 257758 | 260240 | 250675 | 240536 | 253590 | 236633 | 217762 | 200930 | 249621 | 243643 | 235368 | 128016 | 125973 | 84787 | 8075 | 3865 | 458 | 504 | 813 | 231 | 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 +0.4, brooding +0.3, angry +0.3 |
| assistant turn 2 | proud +1.2, grateful +0.4, reflective +0.4 |