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

    Neuronpedia

    INDEX
    Explanations

    terms related to sociology and programming languages such as Lisp

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social science and the concept of society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.81
    rish
    -0.79
    uania
    -0.79
    ifications
    -0.75
    lio
    -0.74
    lishes
    -0.73
    ses
    -0.73
    sing
    -0.72
    eric
    -0.70
    erick
    -0.70
    POSITIVE LOGITS
    merce
    0.91
    auga
    0.84
    awaru
    0.83
    pora
    0.79
    puter
    0.76
    ĸļ
    0.74
    mercial
    0.73
    hyde
    0.73
    URA
    0.73
    urable
    0.72
    Act Density 0.037%

    No Known Activations