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

    Neuronpedia

    INDEX
    Explanations

    food and beverage-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fundamental
    -0.71
     skelet
    -0.66
    eatures
    -0.65
    Specific
    -0.64
     advers
    -0.64
    NF
    -0.63
    ItemImage
    -0.63
    inez
    -0.63
    EGIN
    -0.63
     Construct
    -0.62
    POSITIVE LOGITS
     soup
    1.13
     sandwiches
    1.08
     bottles
    1.08
     biscuits
    1.07
     cans
    1.05
     cereal
    1.04
     vodka
    1.04
     cakes
    1.04
     snacks
    1.02
     drinks
    1.01
    Act Density 0.286%

    No Known Activations