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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names associated with individuals, particularly those with the prefix "Jon" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornia
    -0.98
    ascript
    -0.87
    phia
    -0.82
    eatures
    -0.77
    perture
    -0.73
    Interstitial
    -0.71
    pection
    -0.67
    insula
    -0.66
    Area
    -0.63
    enser
    -0.63
    POSITIVE LOGITS
    sson
    0.82
    witz
    0.78
    onson
    0.71
    kov
    0.71
    gaard
    0.69
    aki
    0.67
    atsu
    0.67
    ubi
    0.66
    trak
    0.64
     Pok
    0.63
    Act Density 0.165%

    No Known Activations