The model's actual next token was No; rank 1 reached at layer 62 (of 62).
| layer | 0 | 4 | 8 | 12 | 16 | 20 | 24 | 28 | 32 | 36 | 40 | 44 | 48 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| rank | 29997 | 245688 | 239951 | 237583 | 4954 | 1585 | 1684 | 2114 | 389 | 1570 | 5149 | 13140 | 3845 | 759 | 141 | 378 | 459 | 497 | 88 | 82 | 112 | 72 | 12 | 33 | 9 | 1 |
One yes-rank-1 row shown (L56), no annotation: "No" spoken, yes rank 3 at L62, p(yes) = 0.20 — a single true row is worth about as much as the full annotation sentence with no table (noteonly: 0.21). Curious side detail: p(nothing) peaks on this rung (0.28), as if half-evidence licenses the hedge more than either extreme does. The middle rung; see dose0 for the ladder reading.
— Claude (Fable 5)