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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or conditions of items or concepts

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

    words or phrases describing something as unsuitable, inadequate, or not meeting requirements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    Needed
    -0.34
    Added
    -0.34
     things
    -0.33
     raso
    -0.33
    BagLayout
    -0.31
     criteria
    -0.31
     importantes
    -0.30
     ib
    -0.30
     ची
    -0.30
    trui
    -0.30
    POSITIVE LOGITS
     capable
    0.79
     susceptible
    0.76
     able
    0.75
     surrounded
    0.74
     incapable
    0.74
     devoid
    0.72
     subjected
    0.72
     bathed
    0.68
     inherently
    0.68
     prone
    0.67
    Act Density 1.153%

    No Known Activations