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

    Neuronpedia

    INDEX
    Explanations

    information related to professions or job titles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating job titles and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    encies
    -0.84
    alties
    -0.82
    events
    -0.79
    tons
    -0.79
    mares
    -0.77
    uden
    -0.71
    ulence
    -0.69
    ayers
    -0.69
    agree
    -0.69
    ency
    -0.68
    POSITIVE LOGITS
     member
    1.03
     teenager
    1.02
     prisoner
    0.95
     liaison
    0.93
     waitress
    0.92
     surrogate
    0.91
     trustee
    0.91
     teacher
    0.90
     substitute
    0.90
     guest
    0.90
    Act Density 0.116%

    No Known Activations