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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating parts of a whole

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.94
     كومونز
    -0.93
    AccessorTable
    -0.91
     مرئيه
    -0.86
    IndentedString
    -0.83
    MLLoader
    -0.80
    WireFormatLite
    -0.78
    клопе
    -0.77
    principalColumn
    -0.77
     intStringLen
    -0.76
    POSITIVE LOGITS
     reich
    0.50
    χα
    0.47
    '])
    0.44
    пря
    0.43
     contingent
    0.43
    neux
    0.43
    тябрь
    0.42
    Context
    0.42
    be
    0.42
    Always
    0.41
    Act Density 0.074%

    No Known Activations