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

    Neuronpedia

    INDEX
    Explanations

    references to personal and identifiable information pertaining to user privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tikang
    -1.08
     فريبيس
    -0.93
     ویکی‌پدی
    -0.92
     חיצוניים
    -0.90
    setVerticalGroup
    -0.87
     chi̍t
    -0.87
    WithIOException
    -0.86
    AddTagHelper
    -0.86
     surla
    -0.85
    ValueStyle
    -0.83
    POSITIVE LOGITS
     privacy
    0.74
     Privacy
    0.65
     data
    0.63
     Datenschutz
    0.60
    enschutzer
    0.56
    Privacy
    0.56
     PRIVACY
    0.55
     Data
    0.53
     Daten
    0.49
    Datenschutz
    0.49
    Act Density 0.734%

    No Known Activations