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

    Neuronpedia

    INDEX
    Explanations

    numbers related to statistics or quantities

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to numerical statistics and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atown
    -0.75
    amount
    -0.68
    istration
    -0.68
    cular
    -0.67
    displayText
    -0.66
    externalActionCode
    -0.65
    lore
    -0.62
     Norn
    -0.61
    imaru
    -0.61
    phy
    -0.61
    POSITIVE LOGITS
     finalists
    0.77
     billion
    0.75
     constituent
    0.73
     pieces
    0.72
     countries
    0.72
     thousand
    0.72
     trillion
    0.71
     acron
    0.71
     million
    0.70
     hundred
    0.70
    Act Density 0.184%

    No Known Activations