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

    Neuronpedia

    INDEX
    Explanations

    measurements and ingredients in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities of ingredients in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theme
    -0.75
    agame
    -0.73
    plays
    -0.73
    pid
    -0.72
    details
    -0.70
    play
    -0.69
    rology
    -0.68
    gnu
    -0.68
    scope
    -0.68
    artist
    -0.68
    POSITIVE LOGITS
    poons
    0.99
    bsp
    0.97
     servings
    0.91
     Organic
    0.89
     potassium
    0.88
     thick
    0.84
     vegetable
    0.82
     cups
    0.81
     oats
    0.81
     Ingredients
    0.81
    Act Density 0.037%

    No Known Activations