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

    Neuronpedia

    INDEX
    Explanations

    numbers related to weights or quantities, specifically the measure 'ounce' and its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of weight, specifically ounces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.73
    neg
    -0.69
    generated
    -0.66
    duction
    -0.62
    omorphic
    -0.62
    actionDate
    -0.62
    ropolis
    -0.61
    western
    -0.60
    incarn
    -0.60
     Nou
    -0.60
    POSITIVE LOGITS
    eki
    0.94
    Quantity
    0.93
     ounce
    0.91
     ounces
    0.89
    cake
    0.79
    MENTS
    0.77
     oz
    0.77
     bottles
    0.77
    poons
    0.74
    glass
    0.71
    Act Density 0.019%

    No Known Activations