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

    Neuronpedia

    INDEX
    Explanations

    mentions of writers and their related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to writers or their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.93
    ibaba
    -0.81
    xon
    -0.79
     Lumpur
    -0.78
    rals
    -0.77
    illon
    -0.74
    inho
    -0.73
    umph
    -0.71
    opping
    -0.70
    Ĭ±
    -0.70
    POSITIVE LOGITS
     writer
    1.23
    writer
    1.07
     laureate
    1.04
     writers
    1.03
     Writer
    0.95
    writ
    0.93
    writers
    0.88
     Writers
    0.86
     fiction
    0.84
    writing
    0.82
    Act Density 0.020%

    No Known Activations