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

    Neuronpedia

    INDEX
    Explanations

    mentions of cocktails and related beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lh
    -0.17
    bak
    -0.15
    oins
    -0.15
    γε
    -0.15
    isko
    -0.14
     bake
    -0.14
    inka
    -0.14
     Sentry
    -0.14
     bergen
    -0.14
    esser
    -0.14
    POSITIVE LOGITS
     cocktails
    0.23
     bartender
    0.22
     cocktail
    0.22
     Cocktail
    0.20
     bart
    0.18
     glasses
    0.18
     spirits
    0.17
    ìŀĶ
    0.17
    tails
    0.17
     Glasses
    0.16
    Act Density 0.058%

    No Known Activations