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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical quantities, particularly the number "dozen"

    oai_token-act-pair · gpt-3.5-turbo

    references to the quantity "dozen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.75
    ains
    -0.66
     thereby
    -0.65
    hes
    -0.63
     Gaming
    -0.60
    thus
    -0.60
     hence
    -0.60
    abis
    -0.59
    ors
    -0.59
     thus
    -0.58
    POSITIVE LOGITS
     dozen
    3.68
    dozen
    3.00
     hundred
    1.97
     thousand
    1.68
     handful
    1.65
     dozens
    1.33
     thirds
    1.15
     Dozens
    1.13
     Hundred
    1.09
    zens
    1.05
    Act Density 0.011%

    No Known Activations