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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food and beverages, particularly in social settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foods
    -0.34
     Foods
    -0.32
     Food
    -0.29
     alimentos
    -0.27
     FOOD
    -0.27
     food
    -0.27
    Food
    -0.27
     comida
    -0.26
    foods
    -0.26
    food
    -0.26
    POSITIVE LOGITS
     drink
    0.40
     drinks
    0.34
     Drink
    0.33
     Bever
    0.33
     beverage
    0.32
     beverages
    0.32
     Beverage
    0.30
     Drinks
    0.29
    drink
    0.29
    Drink
    0.28
    Act Density 0.064%

    No Known Activations