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

    Neuronpedia

    INDEX
    Explanations

    mentions of people being drunk or drunk driving

    oai_token-act-pair · gpt-3.5-turbo

    instances of alcohol consumption and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.80
    Downloadha
    -0.79
     JPM
    -0.74
    akeru
    -0.72
    pha
    -0.68
    DonaldTrump
    -0.67
    isite
    -0.65
     fasc
    -0.65
    semble
    -0.64
     Postal
    -0.64
    POSITIVE LOGITS
     drunk
    1.04
    bott
    0.98
     manslaughter
    0.92
    ards
    0.91
     drinking
    0.89
     underage
    0.88
    cohol
    0.87
     binge
    0.83
     alcohol
    0.80
     drinkers
    0.79
    Act Density 0.027%

    No Known Activations