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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of drinking or drinking-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to drinking and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sharif
    -0.84
    ural
    -0.71
     Parenthood
    -0.69
     notch
    -0.69
    theless
    -0.68
     Postal
    -0.65
    urally
    -0.64
    ality
    -0.64
    cephal
    -0.63
    iasis
    -0.60
    POSITIVE LOGITS
    cohol
    1.16
     bottles
    1.11
    water
    1.09
     beverages
    1.08
     drinkers
    1.07
     alcohol
    1.04
     beverage
    0.99
     Drink
    0.99
     drinking
    0.98
     brewed
    0.98
    Act Density 0.053%

    No Known Activations