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

    Neuronpedia

    INDEX
    Explanations

    words related to influence, motivation, and driving factors

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating influence or motivation behind actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lore
    -0.61
    orage
    -0.57
     Kinnikuman
    -0.56
    tower
    -0.55
    essage
    -0.55
    ITNESS
    -0.55
    oss
    -0.54
     Canad
    -0.54
    issues
    -0.54
    oos
    -0.53
    POSITIVE LOGITS
     by
    1.39
    by
    1.16
    By
    1.06
     BY
    1.03
     By
    1.00
     partly
    0.93
     solely
    0.92
    bys
    0.90
     principally
    0.88
     chiefly
    0.88
    Act Density 0.114%

    No Known Activations