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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of geographical locations or their corresponding postal abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Veterans Administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cold
    -0.77
    lins
    -0.76
    wcsstore
    -0.76
    pins
    -0.74
    cook
    -0.72
    court
    -0.70
    immer
    -0.69
    bread
    -0.68
    tons
    -0.67
    */(
    -0.67
    POSITIVE LOGITS
    VA
    1.31
    Va
    0.92
    BIL
    0.92
    ULT
    0.86
    BILITY
    0.84
    ULTS
    0.84
    ascular
    0.80
    ascus
    0.80
    alkyrie
    0.79
    imation
    0.78
    Act Density 0.007%

    No Known Activations