Rejection sampling

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Autoregressive Samplingmethod0.773
  The mechanism by which LLMs generate text: drawing a token from the next-token distribution and appending it to context repeatedly
• Thompson Samplingmethod0.772
  A Bayesian exploration strategy that samples from the posterior distribution over model parameters to decide actions.
• Sampled-decoding self-reportmethod0.751
  Temperature=0.8 sampled decoding for self-report; reduces collapse moderately but remains discrete and noisy
• Activation Interval Samplingmethod0.749
  Dividing feature activation spectrum into 11 evenly-spaced intervals and sampling uniformly to evaluate monosemanticity across activation levels
• refusal rateconcept0.746
  The percentage of harmful requests that a model refuses to answer, a common safety metric.
• Monte Carlo Cone Samplingmethod0.723
  Procedure for sampling 64 random nonnegative combinations of cone basis vectors to evaluate the full cone distribution
• Refusal directionconcept0.722
  Arditi et al. 2024 finding that refusal behavior is mediated by one direction in LLM activations; exemplar of single-direction causal results
• Experience Sampling Method (ESM)method0.721
  Human psychology method for repeated in-situ self-report; methodological inspiration for the paper's approach