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

    Neuronpedia

    INDEX
    Explanations

    phrases related to food

    oai_token-act-pair · gpt-3.5-turbo

    mentions of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wink
    -0.87
    20439
    -0.77
     Freem
    -0.69
    aird
    -0.69
    itudinal
    -0.69
     Painter
    -0.69
    âĸ¬
    -0.68
     Moff
    -0.68
     Overt
    -0.67
     Caldwell
    -0.66
    POSITIVE LOGITS
    stuff
    1.18
    borne
    1.03
    corn
    1.02
     eaten
    1.01
    grain
    0.94
     tasted
    0.90
     poisoning
    0.89
     starch
    0.88
     additives
    0.87
     allergies
    0.86
    Act Density 0.033%

    No Known Activations