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

    Neuronpedia

    INDEX
    Explanations

    references to professional associations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Association"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.87
    lass
    -0.75
    gone
    -0.74
    stocks
    -0.72
    zers
    -0.70
    tan
    -0.69
    sets
    -0.68
    fare
    -0.67
    castle
    -0.66
    =-=-=-=-=-=-=-=-
    -0.66
    POSITIVE LOGITS
    UTH
    0.86
     membership
    0.84
     Franç
    0.81
     dues
    0.80
     feder
    0.79
    auga
    0.76
     affili
    0.75
     Membership
    0.73
     federation
    0.73
     associations
    0.73
    Act Density 0.052%

    No Known Activations