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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and authors

    oai_token-act-pair · gpt-3.5-turbo

    references to literary genres and associated elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.82
    lain
    -0.80
    xon
    -0.80
    akening
    -0.76
    Downloadha
    -0.70
    ld
    -0.67
     Gund
    -0.67
    ls
    -0.66
    ned
    -0.63
    ALTH
    -0.63
    POSITIVE LOGITS
     fiction
    1.12
     literary
    1.00
     novels
    0.97
     Fiction
    0.94
     laureate
    0.93
    writer
    0.92
     Writers
    0.89
     manuscripts
    0.88
     writers
    0.86
     Literary
    0.86
    Act Density 0.050%

    No Known Activations