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

    Neuronpedia

    INDEX
    Explanations

    specific types of events or actions that are emphasized in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Colbert
    -0.16
    ÃŃd
    -0.15
    acia
    -0.15
     couch
    -0.15
     Gemini
    -0.15
    bery
    -0.15
    -0.14
    [^
    -0.14
    var
    -0.14
    Pk
    -0.14
    POSITIVE LOGITS
    itational
    0.17
    adera
    0.15
    neutral
    0.15
    uci
    0.15
    DownList
    0.15
     StringComparison
    0.15
    ITED
    0.14
    asso
    0.14
     Seeder
    0.14
    ullo
    0.14
    Act Density 0.002%

    No Known Activations