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

    Neuronpedia

    INDEX
    Explanations

    specifics related to costs and alternatives in discussions or comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.87
     Chwiliwch
    -0.79
    ftagPool
    -0.77
    RectangleBorder
    -0.73
     mergeFrom
    -0.64
    writeFieldEnd
    -0.60
     ویکی‌پدیا
    -0.56
    ModelForm
    -0.56
     propOrder
    -0.55
    VIAF
    -0.54
    POSITIVE LOGITS
    featureID
    0.60
     malen
    0.52
    Xaml
    0.52
    indl
    0.50
     mission
    0.49
     側
    0.49
     합니다
    0.48
     Acton
    0.48
     Spire
    0.48
    étal
    0.47
    Act Density 0.153%

    No Known Activations