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

    Neuronpedia

    INDEX
    Explanations

    mentions of meals or food-related activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "meal."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aft
    -0.78
    vernment
    -0.68
    hips
    -0.65
    founded
    -0.63
    itars
    -0.61
    shr
    -0.60
    inates
    -0.60
    herty
    -0.60
     Clifford
    -0.59
    idency
    -0.59
    POSITIVE LOGITS
     meal
    1.47
    worms
    1.26
     Meal
    1.26
     meals
    1.22
    worm
    0.95
    meal
    0.92
     eaten
    0.90
     foods
    0.85
    oleon
    0.84
     dinners
    0.79
    Act Density 0.006%

    No Known Activations