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

    Neuronpedia

    INDEX
    Explanations

    instructions related to cooking and mixing ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.55
     kasarigan
    -0.49
    lacable
    -0.45
    IntoConstraints
    -0.41
    wegs
    -0.40
    gwin
    -0.40
     Conver
    -0.40
    ğraf
    -0.39
    pausal
    -0.39
     convergent
    -0.39
    POSITIVE LOGITS
     cocktails
    0.81
     cocktail
    0.78
     bart
    0.62
     COCK
    0.62
     moj
    0.62
     shots
    0.60
     Moj
    0.60
    カク
    0.60
    cocktail
    0.60
     bartender
    0.60
    Act Density 0.146%

    No Known Activations