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

    Neuronpedia

    INDEX
    Explanations

    references to labor unions and workers' representation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    bilt
    -0.70
    çīĪ
    -0.69
     Flavoring
    -0.66
    hower
    -0.66
    eger
    -0.65
    cold
    -0.65
    ë
    -0.64
    croft
    -0.64
    leon
    -0.62
    erva
    -0.61
    POSITIVE LOGITS
     unions
    1.07
     feder
    1.00
     federation
    1.00
     dues
    0.96
     union
    0.95
     membership
    0.93
     members
    0.85
     representing
    0.83
     organizing
    0.83
     affili
    0.82
    Act Density 0.031%

    No Known Activations