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

    Neuronpedia

    INDEX
    Explanations

    code snippets that specify or declare a "Type" classification

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     nahilalakip
    -1.16
     itſelf
    -0.97
     Monfieur
    -0.95
     Италијани
    -0.86
     himſelf
    -0.84
     Diſ
    -0.84
     myſelf
    -0.82
     Reſ
    -0.82
     ſhe
    -0.79
    DoubleQuotes
    -0.79
    POSITIVE LOGITS
    rawDesc
    0.75
    Type
    0.60
     de
    0.54
     j
    0.51
     a
    0.51
     z
    0.51
     si
    0.49
     san
    0.49
     il
    0.49
    RegressionTest
    0.49
    Act Density 0.003%

    No Known Activations