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

    Neuronpedia

    INDEX
    Explanations

    proper nouns in a mixed list

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arily
    -0.79
    iple
    -0.73
    apers
    -0.73
     Nadu
    -0.69
    imo
    -0.69
    iership
    -0.68
    asons
    -0.66
    ively
    -0.66
    isable
    -0.65
    ASON
    -0.65
    POSITIVE LOGITS
    wana
    0.97
    halla
    0.83
    keley
    0.80
    achev
    0.79
    EGIN
    0.79
    axter
    0.78
    hari
    0.78
    ruary
    0.75
    cham
    0.75
    bent
    0.74
    Act Density 0.142%

    No Known Activations