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

    Neuronpedia

    INDEX
    Explanations

    words related to literary themes or elements

    oai_token-act-pair · gpt-3.5-turbo

    references to literary concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -0.93
    akening
    -0.85
    ned
    -0.81
    rals
    -0.80
    Downloadha
    -0.76
    xon
    -0.75
    ls
    -0.74
    alin
    -0.71
    ldon
    -0.70
    eded
    -0.70
    POSITIVE LOGITS
     literary
    0.99
     fiction
    0.92
     manuscripts
    0.82
     Literary
    0.82
     novels
    0.82
    writer
    0.79
     laureate
    0.79
     Writer
    0.78
     Fiction
    0.78
     writers
    0.76
    Act Density 0.012%

    No Known Activations