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

    Neuronpedia

    INDEX
    Explanations

    references to food and beverage-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foods
    -0.30
     Foods
    -0.30
     meals
    -0.24
    foods
    -0.24
     Food
    -0.23
     comida
    -0.23
     alimentos
    -0.22
     cuisine
    -0.22
     FOOD
    -0.22
    Food
    -0.22
    POSITIVE LOGITS
     drink
    0.41
     beverage
    0.35
     drinks
    0.34
     Beverage
    0.34
     beverages
    0.34
     Drink
    0.34
     Bever
    0.33
    drink
    0.31
     Drinks
    0.29
    Drink
    0.28
    Act Density 0.081%

    No Known Activations