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

    Neuronpedia

    INDEX
    Explanations

    references to internal states or conditions of people and things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VolleyError
    -0.63
    httphttps
    -0.61
    WriteLiteral
    -0.61
    CodeAttribute
    -0.60
    asser
    -0.60
     scythe
    -0.59
     Garibaldi
    -0.58
    routeProvider
    -0.58
    ToAction
    -0.57
     Harms
    -0.57
    POSITIVE LOGITS
     inside
    1.07
     inner
    1.06
     Inner
    1.05
    Inside
    1.04
     Inside
    1.04
    Inner
    1.01
     interior
    0.95
     INSIDE
    0.93
     INNER
    0.93
    inside
    0.93
    Act Density 0.313%

    No Known Activations