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

    Neuronpedia

    INDEX
    Explanations

    words indicating categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
    CppMethod
    -0.70
     combineReducers
    -0.67
    jsxFileName
    -0.63
    runApp
    -0.63
    IntoConstraints
    -0.61
     Photocase
    -0.60
     ApiException
    -0.59
     VIAF
    -0.58
    sidemargin
    -0.58
    POSITIVE LOGITS
     kind
    1.11
     type
    1.06
     kinds
    1.06
     sort
    0.93
     types
    0.91
     tipo
    0.89
     tipos
    0.84
     tipe
    0.84
    type
    0.82
    kinds
    0.81
    Act Density 0.215%

    No Known Activations