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

    Neuronpedia

    INDEX
    Explanations

    names and titles of significant individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.90
     the
    -0.78
     a
    -0.78
     in
    -0.76
     and
    -0.73
    /
    -0.72
    .
    -0.72
     
    -0.71
     to
    -0.70
    :
    -0.69
    POSITIVE LOGITS
     فريبيس
    1.16
    RenderAtEndOf
    1.14
     Roskov
    1.08
    CloseOperation
    1.04
     Houſe
    0.95
     houſe
    0.91
    IUrlHelper
    0.89
     ſever
    0.88
    IntoConstraints
    0.86
     ་་
    0.83
    Act Density 1.094%

    No Known Activations