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

    Neuronpedia

    INDEX
    Explanations

    references to fiction, particularly in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Greenberg
    -0.41
     wür
    -0.40
    Trends
    -0.40
    cili
    -0.40
    جام
    -0.39
    cid
    -0.39
    Lint
    -0.38
     Brin
    -0.37
     نخ
    -0.37
    Trend
    -0.37
    POSITIVE LOGITS
     fiction
    0.63
    ########.
    0.62
    AndEndTag
    0.61
    Pyx
    0.57
    moveToFirst
    0.55
    horabuena
    0.55
    出版年
    0.54
    fiction
    0.54
     Fiction
    0.54
    новништво
    0.52
    Act Density 0.435%

    No Known Activations