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

    Neuronpedia

    INDEX
    Explanations

    key terms related to writers and their works

    oai_token-act-pair · gpt-3.5-turbo

    terms related to writers and writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rals
    -0.79
    illon
    -0.77
     Lumpur
    -0.74
    ADRA
    -0.71
    Ĭ±
    -0.70
    essage
    -0.66
    tnc
    -0.66
    ptions
    -0.65
     CCTV
    -0.65
    ibaba
    -0.65
    POSITIVE LOGITS
    writing
    0.99
    writer
    0.95
    writ
    0.93
     laureate
    0.92
    uscript
    0.87
     fiction
    0.85
     Beware
    0.84
    writers
    0.83
    pub
    0.79
     writer
    0.78
    Act Density 0.054%

    No Known Activations