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

    Neuronpedia

    INDEX
    Explanations

    references to large quantities or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of people or things, particularly in multiples of "hundreds" or "thousands."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igion
    -0.74
    inventoryQuantity
    -0.64
     Manifest
    -0.63
     Situation
    -0.62
     Syndicate
    -0.62
    GEN
    -0.61
    LAND
    -0.61
    llor
    -0.60
    ACTED
    -0.59
    hold
    -0.59
    POSITIVE LOGITS
     thousand
    1.00
    ourcing
    0.91
    eenth
    0.89
     thousands
    0.89
     thous
    0.89
    ourced
    0.82
    uous
    0.81
    uously
    0.81
    ousands
    0.78
    entimes
    0.77
    Act Density 0.031%

    No Known Activations