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

    Neuronpedia

    INDEX
    Explanations

    references to drinking or consumption of liquids, particularly alcoholic beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    drinking water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paragon
    -0.70
     Keyes
    -0.66
    hese
    -0.59
    alya
    -0.58
     Apex
    -0.58
     Wallis
    -0.57
     Farrell
    -0.56
     fields
    -0.56
     Wes
    -0.55
     Alameda
    -0.55
    POSITIVE LOGITS
    Drink
    0.99
     Drink
    0.96
     DRINK
    0.93
    drink
    0.92
    Drinking
    0.83
     drink
    0.82
     bebida
    0.81
    Drinks
    0.78
     Drinking
    0.77
    drinking
    0.77
    Act Density 0.006%

    No Known Activations