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

    Neuronpedia

    INDEX
    Explanations

    ingredients and food items

    oai_token-act-pair · gpt-3.5-turbo

    references to food items or meal components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     events
    -0.74
    events
    -0.70
    Events
    -0.69
     indications
    -0.69
    AIDS
    -0.69
    Develop
    -0.68
     documents
    -0.67
     Contracts
    -0.67
    weapons
    -0.67
     births
    -0.66
    POSITIVE LOGITS
     salad
    1.17
     tablespoon
    1.14
     bowl
    1.13
     mixture
    1.12
     gallon
    1.10
     sprinkle
    1.08
     teaspoon
    1.07
     cup
    1.07
     spoon
    1.06
     pint
    1.04
    Act Density 0.139%

    No Known Activations