method
active
method:contrast-consistent-searchContrast-Consistent Search
Unsupervised probing method from Burns et al. 2023 that identifies directions along which contrast pair representations are far apart
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Contrast Pairsassociated_withPairs of statements with opposite truth values used as input to CCS; e.g., cities and neg_cities paired statements
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.
- Unsupervised probe by Burns et al. to predict latent truth representations; cited as related but limited in generalization
- The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly
- Method comparing brain activity in conscious vs. unconscious conditions.
- Pairs of prompts at different reflection levels used to compute steering vectors.
- A transformation that sharpens and increases the distinction between two types of centers, creating stronger polarity.
- Probe construction method: concept vector at each layer is L2-normalized difference between mean positive and mean negative representations from contrastive system prompts
- Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor
- The problematic possibility of digital minds with superhumanly strong preferences requiring interpersonal utility comparison frameworks