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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements related to weight or quantity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    duction
    -0.70
     inev
    -0.69
    HCR
    -0.66
     architecture
    -0.66
    neg
    -0.63
    gotten
    -0.62
    omorphic
    -0.61
    activ
    -0.61
    actionDate
    -0.60
    western
    -0.60
    POSITIVE LOGITS
     bottles
    1.01
     apiece
    0.95
    cake
    0.94
     bottle
    0.93
     cans
    0.93
     servings
    0.90
     ounces
    0.88
     increments
    0.86
     cups
    0.83
     oz
    0.83
    Act Density 0.037%

    No Known Activations