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

    Neuronpedia

    INDEX
    Explanations

    descriptions of cooking recipes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.85
    osc
    -0.76
    usters
    -0.73
    oscope
    -0.72
    etime
    -0.72
    phe
    -0.71
    gow
    -0.70
    ements
    -0.65
    atform
    -0.65
    leaning
    -0.64
    POSITIVE LOGITS
     recipes
    1.09
     recipe
    1.04
    Ingredients
    0.94
    Recipe
    0.92
     Recipes
    0.85
    reci
    0.83
     recip
    0.79
    isine
    0.79
     ingredient
    0.75
     ingredients
    0.73
    Act Density 0.045%

    No Known Activations