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

    Neuronpedia

    INDEX
    Explanations

    repeated references to specific subjects or items in a discussion

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.82
    :✨
    -0.65
    Autoritní
    -0.63
    djangoproject
    -0.62
    WebElementEntity
    -0.62
     HasFactory
    -0.59
    Уважаемые
    -0.57
    WireFormatLite
    -0.56
     chi̍t
    -0.56
     herren
    -0.55
    POSITIVE LOGITS
    пло
    0.60
     setPassword
    0.59
     فريبيس
    0.58
    ittarius
    0.58
    skor
    0.57
    허
    0.56
     not
    0.56
    hoe
    0.55
    HOE
    0.54
     Ammon
    0.54
    Act Density 0.060%

    No Known Activations