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

    Neuronpedia

    INDEX
    Explanations

    mentions of beverages, particularly specifying a type of drink followed by a drink-related action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize beverages, particularly those served in cups or bottles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilities
    -0.80
    Reviewer
    -0.78
    ahime
    -0.75
    indu
    -0.71
    omnia
    -0.67
    projects
    -0.67
    çīĪ
    -0.65
    iland
    -0.64
    axis
    -0.64
     entrances
    -0.62
    POSITIVE LOGITS
    milo
    0.90
     wine
    0.85
     whisky
    0.82
     freshly
    0.80
     soda
    0.80
     ice
    0.79
     dried
    0.79
     champagne
    0.78
     water
    0.78
     vodka
    0.77
    Act Density 0.113%

    No Known Activations