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

    Neuronpedia

    INDEX
    Explanations

    instances of variable assignments in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     […]
    -0.52
    pari
    -0.49
    CHO
    -0.47
    %@",
    -0.47
     partic
    -0.47
     inclusion
    -0.46
    سب
    -0.45
    appearing
    -0.45
    ⁢
    -0.45
    рая
    -0.44
    POSITIVE LOGITS
    :✨
    0.93
     AssemblyCulture
    0.91
    TypedDataSet
    0.86
     Roskov
    0.86
     autorytatywna
    0.84
     ویکی‌پدی
    0.82
    QMetaType
    0.75
    InputTagHelper
    0.74
     Wikimedijinoj
    0.73
    IUrlHelper
    0.73
    Act Density 0.104%

    No Known Activations