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

    Neuronpedia

    INDEX
    Explanations

    mentions of alcoholic drinks

    oai_token-act-pair · gpt-3.5-turbo

    references to drinking beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sharif
    -0.68
    ural
    -0.66
     Shant
    -0.65
     Brach
    -0.64
     Postal
    -0.62
     notch
    -0.62
    roe
    -0.60
    REM
    -0.59
    izons
    -0.58
    theless
    -0.58
    POSITIVE LOGITS
    cohol
    1.14
     drinkers
    1.10
     bottles
    1.05
     Drink
    1.02
     beverages
    0.97
    water
    0.95
     drink
    0.94
     alcohol
    0.92
     drinks
    0.91
    bott
    0.90
    Act Density 0.022%

    No Known Activations