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

    Neuronpedia

    INDEX
    Explanations

    people's occupations or professions

    oai_token-act-pair · gpt-3.5-turbo

    statements about individuals who hold leadership or professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Russians
    -0.72
     routed
    -0.71
     humiliating
    -0.70
     favour
    -0.70
     degrading
    -0.64
    ulus
    -0.64
     unbeliev
    -0.63
     forcibly
    -0.63
     bandwagon
    -0.62
    ppings
    -0.62
    POSITIVE LOGITS
     blogging
    0.83
    rint
    0.75
    aspers
    0.70
    owship
    0.69
    interstitial
    0.69
    tml
    0.68
    director
    0.68
     lawy
    0.67
    inical
    0.67
    arcer
    0.66
    Act Density 0.368%

    No Known Activations