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

    Neuronpedia

    INDEX
    Explanations

    information related to academic publications, including publishers and publication details

    oai_token-act-pair · gpt-3.5-turbo

    references to publishing details and academic sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qqa
    -0.76
    ratom
    -0.75
    lyak
    -0.73
    ggle
    -0.69
     medically
    -0.68
    unts
    -0.65
    AMI
    -0.65
    twitch
    -0.65
     biod
    -0.64
    auna
    -0.64
    POSITIVE LOGITS
     Literary
    1.18
     Publishing
    1.08
     Publishers
    1.06
     Books
    0.98
     Journals
    0.98
     paperback
    0.95
     Eag
    0.93
    published
    0.92
    Magazine
    0.92
     Gutenberg
    0.91
    Act Density 0.365%

    No Known Activations