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

    Neuronpedia

    INDEX
    Explanations

    occupations and professional roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to professions and job roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.78
    eways
    -0.72
     TEXT
    -0.65
    nings
    -0.63
    Tokens
    -0.63
    isms
    -0.63
     ABV
    -0.62
     Zot
    -0.61
     Toys
    -0.61
    eworks
    -0.61
    POSITIVE LOGITS
    assador
    0.87
     lover
    0.82
     dancer
    0.81
    nostic
    0.81
     athlete
    0.81
    atcher
    0.81
     consultant
    0.80
     runner
    0.79
     practition
    0.79
     guy
    0.79
    Act Density 0.576%

    No Known Activations