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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of workers or unions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of labor or worker organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geo
    -0.73
    eb
    -0.71
    rawdownloadcloneembedreportprint
    -0.68
     Cardinal
    -0.66
    indu
    -0.64
    arie
    -0.63
     NJ
    -0.62
    eele
    -0.62
     Vir
    -0.61
     Mald
    -0.61
    POSITIVE LOGITS
     Workers
    1.11
    hops
    1.03
     Worker
    1.01
    workers
    0.93
    worker
    0.90
    chwitz
    0.86
    ysc
    0.81
    TPPStreamerBot
    0.78
    paces
    0.78
    Work
    0.77
    Act Density 0.015%

    No Known Activations