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

    Neuronpedia

    INDEX
    Explanations

    mentions of meals or eating-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to meals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignty
    -0.77
    idency
    -0.70
    inates
    -0.69
     bluff
    -0.66
     Jed
    -0.65
     Moff
    -0.64
    itars
    -0.63
    rity
    -0.60
     Morse
    -0.60
    vernment
    -0.58
    POSITIVE LOGITS
    worms
    1.25
     meal
    1.14
     meals
    1.09
     Meal
    1.06
     eaten
    0.99
     buffet
    0.95
    worm
    0.95
    mares
    0.92
    cloth
    0.84
    meat
    0.81
    Act Density 0.013%

    No Known Activations