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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal expressions or inquiries about perceptions, experiences, or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.52
     holt
    -0.48
    requestCode
    -0.46
    RectangleBorder
    -0.42
    ності
    -0.41
    fact
    -0.41
    GEBURTSDATUM
    -0.40
     ←
    -0.40
    Enders
    -0.40
    êche
    -0.40
    POSITIVE LOGITS
    Jîn
    0.77
     ModelExpression
    0.68
    IVEREF
    0.66
     Biôgrafia
    0.66
     tartalomajánló
    0.66
    aarrggbb
    0.65
    Personensuche
    0.64
    belec
    0.64
     CommonModule
    0.64
     estekak
    0.63
    Act Density 0.227%

    No Known Activations