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

    Neuronpedia

    INDEX
    Explanations

    mentions of coffee-related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "coffee" and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppable
    -0.80
    ROR
    -0.79
    orse
    -0.74
     Caldwell
    -0.72
     newcom
    -0.68
    yss
    -0.68
    ollow
    -0.67
    Filename
    -0.66
    veh
    -0.65
    Population
    -0.65
    POSITIVE LOGITS
     beans
    1.20
     Beans
    1.10
     bean
    1.01
     brewed
    1.01
     drip
    0.96
     coffee
    0.94
    weed
    0.90
     cups
    0.90
    cake
    0.90
     drinkers
    0.88
    Act Density 0.015%

    No Known Activations