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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities of substances

    oai_token-act-pair · gpt-3.5-turbo

    quantities and measurements related to substances in both solid and liquid forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estate
    -0.73
    exit
    -0.68
     architecture
    -0.65
     Doodle
    -0.65
    Ü
    -0.63
     priorities
    -0.63
    eering
    -0.63
    idth
    -0.63
     architectures
    -0.62
    attribute
    -0.62
    POSITIVE LOGITS
     apiece
    1.08
     increments
    0.97
     bottles
    0.93
    poons
    0.90
     doses
    0.89
     ABV
    0.87
     servings
    0.87
     ounces
    0.86
     per
    0.86
    oz
    0.85
    Act Density 0.070%

    No Known Activations