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

    Neuronpedia

    INDEX
    Explanations

    words related to organizations, specifically associations or groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various associations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.81
    stocks
    -0.77
    tro
    -0.67
    lass
    -0.67
    =-=-=-=-=-=-=-=-
    -0.66
    sets
    -0.66
    haven
    -0.65
    gone
    -0.65
    agram
    -0.64
    fare
    -0.63
    POSITIVE LOGITS
    UTH
    0.86
     membership
    0.83
     feder
    0.82
    eer
    0.80
     dues
    0.79
    uthor
    0.77
     associations
    0.77
     federation
    0.77
     Membership
    0.76
     affili
    0.76
    Act Density 0.033%

    No Known Activations