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

    Neuronpedia

    INDEX
    Explanations

    food items and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    food items and meal descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     experien
    -0.77
     territ
    -0.73
     Oversight
    -0.73
     asset
    -0.72
     departures
    -0.71
     intelligence
    -0.70
     timelines
    -0.70
     observer
    -0.70
    ģ«
    -0.69
     operative
    -0.69
    POSITIVE LOGITS
     delicious
    0.97
    Cola
    0.95
     cakes
    0.92
    Sweet
    0.91
     tasty
    0.89
     Cooking
    0.88
     tart
    0.87
     jelly
    0.85
     nutritious
    0.85
    Recipe
    0.85
    Act Density 0.828%

    No Known Activations