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

    Neuronpedia

    INDEX
    Explanations

    statements involving the ending of commands or functions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.78
    Życiorys
    -0.74
    дарь
    -0.73
     الرياضيه
    -0.69
    principalTable
    -0.69
    Jîn
    -0.68
     transférez
    -0.68
     Theſe
    -0.67
    betical
    -0.66
    TypedDataSet
    -0.65
    POSITIVE LOGITS
    enderror
    0.64
    ü
    0.49
     commerciales
    0.46
    InSection
    0.42
     múl
    0.41
    ere
    0.40
    ほど
    0.39
    ffic
    0.39
    (
    0.37
    程
    0.37
    Act Density 0.022%

    No Known Activations