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

    Neuronpedia

    INDEX
    Explanations

    references to government agencies, specifically bureaus

    oai_token-act-pair · gpt-3.5-turbo

    references to various government or investigative bureaus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isks
    -0.73
     Vader
    -0.70
    wcsstore
    -0.65
    isable
    -0.64
    IFE
    -0.64
    terday
    -0.64
     wart
    -0.64
     Horus
    -0.63
    orem
    -0.63
     Balkans
    -0.62
    POSITIVE LOGITS
    ureau
    1.10
    oreal
    0.92
    cr
    0.80
    xia
    0.76
    ration
    0.75
    riet
    0.73
    asketball
    0.73
     Bureau
    0.72
    é¾įåĸļ士
    0.70
    bryce
    0.69
    Act Density 0.016%

    No Known Activations