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

    Neuronpedia

    INDEX
    Explanations

    mentions of the quantity "many"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "many."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.86
    etry
    -0.80
    adish
    -0.77
    iasis
    -0.70
    arium
    -0.68
    ope
    -0.67
    atism
    -0.67
    agate
    -0.66
    agraph
    -0.65
    abus
    -0.65
    POSITIVE LOGITS
     times
    0.88
    body
    0.75
     facets
    0.75
     unanswered
    0.72
     thous
    0.72
     thousands
    0.71
     aspects
    0.71
     dozen
    0.70
     nights
    0.69
     millions
    0.68
    Act Density 0.054%

    No Known Activations