Incommensurability

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

• nondeterminismconcept0.777
  Inherent in Linda because an in statement chooses one matching tuple arbitrarily; essential for many parallel patterns.
• incoherenceconcept0.771
  Nonsensical or unphysical model outputs that result when interventions cross voids in activation space.
• Coherenceconcept0.747
  A property that makes a segment of space stand out as a center; determined by symmetry, connectedness, convexity, etc.
• "For interpretability, I don't think we even have the right definitions."quote0.733
  Ian Goodfellow quote used to illustrate the pre-paradigmatic state of interpretability research
• monosemanticityconcept0.731
  Interpretability property where a latent feature represents a single semantic concept; benchmarked across architectures.
• Persuadabilityconcept0.731
  The degree to which a system can be influenced by signals from brute force to rational argument; correlates with cognitive sophistication.
• ambiguityconcept0.729
  Multiple possible meanings for words like Alice, disambiguated by context; harder when grammar and meaning intertwine
• irregularity in arrangementconcept0.729
  Non-uniform placement, like cars parked irregularly, that increases relationship and life.