paper
referenced-only
paper:log-p-x-c-p-x-clog p ( x | c ) p ( x | c ′ ) = log p ( x | c ) − log p ( x | c ′ ) ≈ γN − α ( −|{ i ∈ { 1
Similar preprints — Semantic Scholar
Cited by (1)
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
In-context learning and activation steering are the same operation on a latent-concept belief: context adds log-likelihood evidence while a steering vector adds a constant shift to the log prior odds,