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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    atorial
    -0.57
    ators
    -0.54
    ounty
    -0.48
    icidal
    -0.48
    icides
    -0.48
    ricular
    -0.48
    onest
    -0.47
    ately
    -0.47
    ership
    -0.47
    naire
    -0.46
    POSITIVE LOGITS
     AFB
    0.53
    shire
    0.50
    sburg
    0.48
     Andrews
    0.47
    issance
    0.45
     Lans
    0.43
    gomery
    0.41
    endor
    0.40
    bourg
    0.40
    DEF
    0.39
    Act Density 8.257%

    No Known Activations