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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Pierre

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agy
    -0.84
    baugh
    -0.80
    wcs
    -0.79
    ichael
    -0.74
    itness
    -0.73
    iculty
    -0.71
    tub
    -0.69
    Discussion
    -0.69
    akens
    -0.69
    opathy
    -0.69
    POSITIVE LOGITS
     Trudeau
    0.99
     Pierre
    0.94
     McGu
    0.86
     Francois
    0.82
     Erd
    0.77
     François
    0.77
     Bou
    0.73
    lette
    0.72
     Santos
    0.72
     Laurent
    0.72
    Act Density 0.023%

    No Known Activations