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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enment
    -0.81
     Deliver
    -0.73
    Ļ½
    -0.68
    Interstitial
    -0.68
     coli
    -0.67
    CLA
    -0.64
     Ai
    -0.62
    entimes
    -0.62
    route
    -0.61
    Dialogue
    -0.61
    POSITIVE LOGITS
     balloons
    0.73
     brackets
    0.69
     inflated
    0.69
     graphs
    0.68
     underest
    0.65
    é¾įå
    0.65
    emark
    0.65
     sums
    0.64
    oola
    0.64
     snapshots
    0.63
    Act Density 0.394%

    No Known Activations