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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions of food recipes and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esModule
    -0.16
    éłĺ
    -0.15
     صÙĨ
    -0.14
    ksam
    -0.14
    .nano
    -0.14
    #
    -0.13
     cigaret
    -0.13
    rames
    -0.13
    eyn
    -0.13
    owler
    -0.12
    POSITIVE LOGITS
     ingredients
    0.44
     herbs
    0.32
    ingredients
    0.32
     spices
    0.32
     ing
    0.32
     components
    0.30
     Ingredients
    0.29
     ingredient
    0.27
     season
    0.27
     vegetables
    0.27
    Act Density 0.118%

    No Known Activations