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

    Neuronpedia

    INDEX
    Explanations

    references to food and nutrition-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Wink
    -1.09
     Caldwell
    -1.02
    aird
    -0.98
     Moff
    -0.97
    20439
    -0.96
     Voting
    -0.96
     Rowe
    -0.95
     Overt
    -0.94
    acular
    -0.93
     Freem
    -0.91
    POSITIVE LOGITS
    stuff
    1.57
    borne
    1.38
     eaten
    1.34
    corn
    1.30
     tasted
    1.26
    eteria
    1.21
    grain
    1.19
     cake
    1.17
     allergies
    1.16
     meals
    1.11
    Act Density 0.965%

    No Known Activations