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

    Neuronpedia

    INDEX
    Explanations

    references to food and special occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soup
    -0.17
    Soup
    -0.17
     spaghetti
    -0.16
    éħĴ
    -0.15
    Dice
    -0.15
    алов
    -0.15
     Soup
    -0.15
     Salad
    -0.14
     Dice
    -0.14
    dice
    -0.14
    POSITIVE LOGITS
     dough
    0.33
     Dough
    0.29
     Dunk
    0.23
     pastry
    0.22
     past
    0.22
    pa
    0.21
     Kris
    0.21
     glazed
    0.21
     yeast
    0.20
     cron
    0.20
    Act Density 0.043%

    No Known Activations