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

    Neuronpedia

    INDEX
    Explanations

    instances where the text discusses a numerical quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a large number or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quote
    -0.77
    âĺ
    -0.70
    interstitial
    -0.67
    DragonMagazine
    -0.64
    cause
    -0.63
    SF
    -0.61
    Tomorrow
    -0.61
    MpServer
    -0.61
    FOR
    -0.60
    Pri
    -0.59
    POSITIVE LOGITS
     years
    0.99
     exhausting
    0.99
     unsuccessful
    0.95
     generations
    0.94
     hiatus
    0.88
     seasons
    0.88
     decades
    0.88
     stint
    0.87
     iterations
    0.87
     periods
    0.87
    Act Density 0.115%

    No Known Activations