concept
active
concept:global-logit-shiftglobal logit shift
The methodological confound identified by this paper: injection biases model toward 'YES' for any binary question regardless of content
Neighborhood — ranked by edge-count
Claims (1)
claim
- Primary negative finding reinterpreted as methodological claim: binary paradigm is invalid for testing introspection
Methods (3)
method
- Sentence Localization Taskassociated_withNovel task asking which of 10 sentences received injection, cycling injection through all positions to average out positional bias
- Strength Comparison Taskassociated_withNovel task asking which of two sentences received a stronger injection, using matched-pairs design to control for positional bias
- Binary Detection Taskassociated_withTask paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded
Concepts (1)
concept
- differential sensitivitycontradictsThe capacity to distinguish which of multiple sentences received injection or which received stronger injection, contrasted with binary detection
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Samples from interpolated logits of original and abliterated models at α.
- Full distribution over tokens 0-9 at first generation step; contains more information than any single sampled token
- Method from sparse feature circuits that SCR automates.
- Training-free monitor that token-forces an eval-aware sentence and computes its probability at each CoT sentence boundary.
- Parameter-free loss transformation applied to each task loss to equalize scales
- Dot product of summed decoder vector with unembedding vector, following Hanna et al.
- Prior method extrapolating beyond the original model in logit space to surface rare behaviors.
- The paper's method: interpolate between two models in logit space, measure compliance where common, and extrapolate to the original.