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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly last names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pixie
    -0.77
     curfew
    -0.75
    worldly
    -0.74
    angular
    -0.73
     Paso
    -0.68
     Assassins
    -0.66
    iago
    -0.66
    oppable
    -0.64
     Filipino
    -0.63
    ables
    -0.63
    POSITIVE LOGITS
    stein
    1.29
     Katz
    1.09
    baum
    1.00
     Goldstein
    0.99
     Shapiro
    0.98
    owitz
    0.97
    hetti
    0.91
    wald
    0.90
     Eisen
    0.89
    itsch
    0.88
    Act Density 0.045%

    No Known Activations