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

    Neuronpedia

    INDEX
    Explanations

    references to labor unions or activities related to unions

    oai_token-act-pair · gpt-3.5-turbo

    references to unions and union-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.77
    hower
    -0.76
    cold
    -0.72
    olitics
    -0.72
     Flavoring
    -0.71
    erva
    -0.69
    »Ĵ
    -0.65
    onso
    -0.65
    articles
    -0.65
    thora
    -0.64
    POSITIVE LOGITS
     federation
    1.07
     unions
    1.07
     union
    1.00
     feder
    1.00
     membership
    0.95
     dues
    0.84
     anthem
    0.81
     organizer
    0.79
    union
    0.79
     Confederation
    0.78
    Act Density 0.024%

    No Known Activations