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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific professions or roles related to various disciplines or areas of expertise

    oai_token-act-pair · gpt-3.5-turbo

    words related to various occupations and professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bernatorial
    -0.77
    adesh
    -0.72
    yss
    -0.70
    reci
    -0.69
     example
    -0.63
    abus
    -0.61
    worthiness
    -0.60
    READ
    -0.59
    okemon
    -0.59
     descriptor
    -0.59
    POSITIVE LOGITS
     who
    1.11
    hips
    1.07
    ervatives
    0.97
    hip
    0.95
     alike
    0.93
     whose
    0.89
    ervative
    0.88
    paces
    0.87
    who
    0.86
     specializing
    0.84
    Act Density 0.306%

    No Known Activations