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

    Neuronpedia

    INDEX
    Explanations

    references to fiction

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "fiction" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.70
    Accessory
    -0.66
     downed
    -0.66
    fty
    -0.64
    umm
    -0.64
    hens
    -0.63
    rals
    -0.63
    realDonaldTrump
    -0.62
    baugh
    -0.62
    ermanent
    -0.61
    POSITIVE LOGITS
     fiction
    1.07
     anthology
    0.92
     Fiction
    0.92
     novels
    0.88
     novelist
    0.84
    fiction
    0.81
     imagin
    0.80
    istically
    0.80
     Writers
    0.78
    Writ
    0.78
    Act Density 0.022%

    No Known Activations