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

    Neuronpedia

    INDEX
    Explanations

    notable people from various professions and locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names associated with various professions or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zers
    -0.82
    erity
    -0.79
    ize
    -0.72
    olars
    -0.71
    ":"/
    -0.71
    OTUS
    -0.70
    pring
    -0.69
    ords
    -0.69
    obin
    -0.68
    enthal
    -0.68
    POSITIVE LOGITS
     respectively
    0.90
     etc
    0.83
     albeit
    0.81
     whose
    0.75
     lecturer
    0.74
     specializing
    0.73
    76561
    0.73
     founded
    0.72
     moreover
    0.70
     educator
    0.67
    Act Density 0.214%

    No Known Activations