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

    Neuronpedia

    INDEX
    Explanations

    words related to alcohol consumption and alcohol-related issues

    oai_token-act-pair · gpt-3.5-turbo

    references to alcohol and its related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Telecom
    -0.75
     Doct
    -0.74
    arity
    -0.69
     Pon
    -0.67
     Postal
    -0.66
     Earthqu
    -0.66
    iron
    -0.66
     Canaver
    -0.65
     Aj
    -0.64
     Tyson
    -0.64
    POSITIVE LOGITS
    ocaust
    1.10
    cohol
    1.07
     beverages
    1.06
     dehyd
    1.03
     beverage
    1.03
     alcohol
    1.01
     poisoning
    0.95
     intoxication
    0.94
     intox
    0.94
     consumption
    0.94
    Act Density 0.022%

    No Known Activations