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

    Neuronpedia

    INDEX
    Explanations

    names or descriptions related to cocktails

    oai_token-act-pair · gpt-3.5-turbo

    references to cocktails and mixed drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħ
    -0.88
    Prev
    -0.85
    ership
    -0.73
     Prev
    -0.70
    teness
    -0.69
    uthor
    -0.67
    nces
    -0.66
    ths
    -0.65
     Kun
    -0.65
    Whe
    -0.65
    POSITIVE LOGITS
     cocktail
    3.83
     cocktails
    3.28
     Cock
    1.62
     bartender
    1.56
     gin
    1.55
     vodka
    1.53
     bart
    1.52
     drinks
    1.43
     conco
    1.42
     brunch
    1.40
    Act Density 0.017%

    No Known Activations