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

    Neuronpedia

    INDEX
    Explanations

    mentions of coffee and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rockwell
    -0.56
    atoma
    -0.55
    riwal
    -0.54
     Rockland
    -0.51
     Reptile
    -0.51
     Magdeburg
    -0.51
     ples
    -0.50
     Grèce
    -0.49
     Victor
    -0.48
    ปลา
    -0.47
    POSITIVE LOGITS
     coffee
    2.13
     Coffee
    1.96
    Coffee
    1.93
    coffee
    1.86
     coffees
    1.80
     COFFEE
    1.78
     coffe
    1.67
     Coffe
    1.65
     caffeine
    1.62
     barista
    1.59
    Act Density 0.084%

    No Known Activations