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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REE
    -0.78
    ï¸ı
    -0.70
    hovah
    -0.67
    sburgh
    -0.67
    ignty
    -0.66
     Thumbnails
    -0.66
    IGH
    -0.66
     Chaser
    -0.63
    respect
    -0.62
    ï¸
    -0.61
    POSITIVE LOGITS
    ovic
    1.29
    owitz
    1.10
    ovi
    1.09
    agement
    1.02
    ovich
    1.00
    ufact
    0.94
    ovsky
    0.93
    owski
    0.92
    thal
    0.92
    ews
    0.90
    Act Density 0.046%

    No Known Activations