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

    Neuronpedia

    INDEX
    Explanations

    specific food-related descriptors and concepts related to meals and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPA
    -0.16
    piel
    -0.16
     Herb
    -0.16
    atte
    -0.15
     Dice
    -0.14
     decorators
    -0.14
    olvers
    -0.14
    ait
    -0.14
    adil
    -0.14
     Salad
    -0.14
    POSITIVE LOGITS
     food
    0.50
     foods
    0.45
    food
    0.38
     fare
    0.37
     grub
    0.37
     FOOD
    0.35
    -food
    0.34
     sust
    0.31
     treats
    0.31
    Food
    0.29
    Act Density 0.326%

    No Known Activations