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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job applications and work experience

    oai_token-act-pair · gpt-3.5-turbo

    references to resumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rams
    -0.75
    bidden
    -0.69
    ortium
    -0.68
    gran
    -0.66
    cart
    -0.66
    itsch
    -0.65
    era
    -0.65
    usky
    -0.64
    atorial
    -0.63
    artisan
    -0.62
    POSITIVE LOGITS
     resume
    1.34
     resumes
    1.19
    olicy
    0.95
    isode
    0.86
     resumed
    0.76
     manif
    0.75
    pring
    0.75
     mosqu
    0.75
    natureconservancy
    0.70
     hemor
    0.70
    Act Density 0.004%

    No Known Activations