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

    Neuronpedia

    INDEX
    Explanations

    food-related descriptors and references to various meal types and dietary considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Instruction
    -0.15
     Den
    -0.15
    597
    -0.15
     Environment
    -0.14
     fur
    -0.14
    amo
    -0.14
    ateurs
    -0.14
     dedicated
    -0.13
    asting
    -0.13
    used
    -0.13
    POSITIVE LOGITS
     foods
    0.38
     food
    0.33
     dishes
    0.28
    food
    0.28
     dish
    0.27
     fare
    0.27
    foods
    0.26
     FOOD
    0.25
    é£Łåĵģ
    0.25
    -food
    0.24
    Act Density 0.151%

    No Known Activations