Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The neuron activates for concepts related to stability or instability, particularly in scientific and technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "stable" and related concepts of stability or instability.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     Grou
    -0.42
    礼
    -0.36
    RSpec
    -0.35
     gil
    -0.35
    AutoField
    -0.35
     resourceCulture
    -0.34
    ActionCreators
    -0.34
     CURIAM
    -0.33
     بتاريخ
    -0.33
     Gil
    -0.33
    POSITIVE LOGITS
     stability
    1.62
    Stability
    1.51
     Stability
    1.46
    stability
    1.46
     instability
    1.42
    Stable
    1.42
     unstable
    1.39
     stabilisation
    1.39
     stabili
    1.38
     stabilize
    1.38
    Act Density 0.184%

    No Known Activations