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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "writing" with varying emphasis in context

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĭ±
    -0.89
    agara
    -0.78
    EGA
    -0.78
    illon
    -0.74
    azar
    -0.73
    abe
    -0.72
    rals
    -0.70
    rolet
    -0.69
    Afee
    -0.67
     Shinra
    -0.67
    POSITIVE LOGITS
     poems
    0.88
    writing
    0.88
    smanship
    0.82
     penned
    0.82
    writer
    0.81
     essays
    0.79
     poem
    0.78
     poetry
    0.76
     letters
    0.76
     writing
    0.75
    Act Density 0.040%

    No Known Activations