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

    Neuronpedia

    INDEX
    Explanations

    references to people, particularly names and details about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.63
     Girard
    -0.61
     Hildebrand
    -0.60
    YK
    -0.60
     Micron
    -0.57
     YR
    -0.57
     Wilcox
    -0.57
     Wilkins
    -0.56
     himo
    -0.54
    YD
    -0.54
    POSITIVE LOGITS
    arty
    0.83
     Parry
    0.82
     Dany
    0.78
    bory
    0.77
    amy
    0.77
    meny
    0.76
    endy
    0.76
    tory
    0.76
    lary
    0.76
    mony
    0.76
    Act Density 0.839%

    No Known Activations