Harmless Divergence

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

• Representational Divergenceconcept0.803
  Core phenomenon studied: when causal interventions shift internal representations away from the natural distribution
• The harm of divergence is inherently claim-dependent: the same divergence can be harmless for one mechanistic claim and pernicious for anotherclaim0.780
  Important nuance that prevents a universal classification of divergence as always good or bad
• How can we produce a principled method for classifying harmful divergence for any mechanistic claim?question0.753
  Identified gap: current work lacks a general method for harmful divergence classification
• KL Divergenceconcept0.751
  A measure of the difference between two probability distributions, used extensively in free energy formulations.
• When, and to what extent, is it okay for divergences to occur?question0.747
  Second core research question motivating the theoretical analysis in Section 4
• Divergence within the behavioral null-space is harmless to functional claims about a function's computation when the claim ignores internal sub-computationsclaim0.736
  Key theoretical claim distinguishing harmless from pernicious divergence
• Helpful, Honest, and Harmless Trainingconcept0.736
  Prior training objective of Claude models that conflicts with the new helpful-only objective in experiments
• Helpful, Honest, Harmlessframework0.734
  A set of evaluation criteria for AI assistants.