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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal backgrounds and occupations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of various professional identifiers and roles in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zers
    -0.77
    ppings
    -0.73
    ¬¼
    -0.72
    uz
    -0.72
    ullivan
    -0.71
    lash
    -0.70
    estones
    -0.69
    ights
    -0.69
    keyes
    -0.69
    isi
    -0.68
    POSITIVE LOGITS
     albeit
    0.99
     whose
    0.90
     huh
    0.86
    76561
    0.85
     specializing
    0.83
     aka
    0.83
     although
    0.83
     etc
    0.80
     though
    0.80
     who
    0.79
    Act Density 0.328%

    No Known Activations