arXiv:2603.13259v2 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge in a specific way: displacement vectors from the query-only representation maintain approximately equal magnitude but rotate apart in direction. The angular separation grows through mid-depth, and late layers resolve the asymmetric outcome -a logit-lens preference that, in the incorrect run, falls far below the naive prior of equal probability, corresponding
Source: arXiv cs.AI — read the full report at the original publisher.