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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "alcohol"

    oai_token-act-pair · gpt-3.5-turbo

    mentions and discussions related to alcohol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dear
    -0.71
    arity
    -0.71
     Dear
    -0.68
     Telecom
    -0.67
     Annual
    -0.67
     Voice
    -0.67
    AF
    -0.66
     Fi
    -0.65
     Aj
    -0.65
     Kaw
    -0.64
    POSITIVE LOGITS
     alcohol
    1.35
    cohol
    1.20
    alcohol
    1.17
     drinkers
    1.10
     beverages
    1.08
    ocaust
    1.08
     liquor
    1.06
     beverage
    1.04
     intoxication
    1.03
     intox
    1.02
    Act Density 0.009%

    No Known Activations