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

    Neuronpedia

    INDEX
    Explanations

    mentions of cooking or food preparation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     drinking
    -0.53
    drinking
    -0.50
     فرو
    -0.49
     Drinking
    -0.49
     drank
    -0.48
     beber
    -0.47
     payers
    -0.47
    Drinking
    -0.47
    Lunch
    -0.46
     uống
    -0.46
    POSITIVE LOGITS
     cooking
    2.01
     cook
    1.84
     Cooking
    1.76
     recipes
    1.73
     cooks
    1.71
     recipe
    1.71
    Cooking
    1.70
    cooking
    1.67
     COOK
    1.64
    cook
    1.62
    Act Density 0.202%

    No Known Activations