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

    Neuronpedia

    INDEX
    Explanations

    mentions of different associations (organizations or groups)

    oai_token-act-pair · gpt-3.5-turbo

    references to various associations or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.85
    sets
    -0.81
    fare
    -0.76
    lass
    -0.74
    gone
    -0.73
    stocks
    -0.73
    aunder
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    haven
    -0.68
    tan
    -0.66
    POSITIVE LOGITS
     membership
    0.88
     dues
    0.87
     Franç
    0.86
    UTH
    0.85
     Membership
    0.77
     Board
    0.74
     feder
    0.74
     associations
    0.72
     boycott
    0.71
     board
    0.70
    Act Density 0.062%

    No Known Activations