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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those named Hammond or Clarkson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obos
    -0.83
    ozo
    -0.76
    luster
    -0.72
    culosis
    -0.71
    pport
    -0.69
    hift
    -0.68
    uary
    -0.68
    geries
    -0.67
    atown
    -0.66
    eper
    -0.65
    POSITIVE LOGITS
    shire
    1.07
    monds
    1.06
    sburg
    1.04
     Hammond
    1.02
    s
    0.78
    wich
    0.73
    ļé
    0.70
    elin
    0.69
    ding
    0.69
    thouse
    0.68
    Act Density 0.039%

    No Known Activations