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

    Neuronpedia

    INDEX
    Explanations

    XML-like attribute names and their associated values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.66
    uevo
    -0.60
    TextBoxColumn
    -0.60
    mergeFrom
    -0.57
    sproz
    -0.56
    的用户
    -0.55
     ($('#
    -0.55
    (--
    -0.54
    edos
    -0.54
     textStatus
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
    expandindo
    0.76
    Diwedd
    0.60
     efec
    0.52
    BeginContext
    0.50
     animali
    0.50
    ঐ
    0.49
     frontale
    0.48
     Walkover
    0.48
     يتيمه
    0.47
    Act Density 0.007%

    No Known Activations