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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating personal insights or opinions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     tal
    -0.48
     man
    -0.45
    LITERAL
    -0.43
    isticated
    -0.41
     AssemblyTitle
    -0.41
    setCellValue
    -0.40
    skraft
    -0.40
     Euro
    -0.40
     scala
    -0.40
    kolan
    -0.40
    POSITIVE LOGITS
     فريبيس
    1.09
    +#+#
    1.02
     Meksiku
    1.02
    ValueStyle
    0.89
    InjectAttribute
    0.86
     itſelf
    0.84
     nahilalakip
    0.84
     Normdatei
    0.84
     Lightboxes
    0.81
     kaarangay
    0.81
    Act Density 1.843%

    No Known Activations