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

    Neuronpedia

    INDEX
    Explanations

    actions related to drinking or sipping beverages

    oai_token-act-pair · gpt-3.5-turbo

    activities related to consuming beverages and food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Camer
    -0.71
     guiIcon
    -0.68
    Jr
    -0.67
     Vaj
    -0.66
    */(
    -0.66
     morphology
    -0.66
     Defenders
    -0.65
     Commissioners
    -0.65
    CLASS
    -0.64
     Dimensions
    -0.64
    POSITIVE LOGITS
    wine
    1.11
     popcorn
    1.02
    cake
    1.01
     beverage
    1.00
     soda
    0.98
     snacks
    0.97
     drinks
    0.96
    Food
    0.95
     tasting
    0.93
     meals
    0.91
    Act Density 0.341%

    No Known Activations