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

    proper nouns, particularly names of individuals or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ively
    -0.93
    ion
    -0.93
    iveness
    -0.91
    aired
    -0.89
    elf
    -0.84
    ivity
    -0.84
    ional
    -0.82
    lie
    -0.80
    ework
    -0.78
    vest
    -0.78
    POSITIVE LOGITS
    hyde
    0.84
     Hasan
    0.72
     Penal
    0.71
    uay
    0.71
     Canaver
    0.69
     Cabrera
    0.66
    cember
    0.66
     Bane
    0.66
     Williamson
    0.65
     Wast
    0.64
    Act Density 0.012%

    No Known Activations