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

    Neuronpedia

    INDEX
    Explanations

    descriptions of food and its preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sugar
    -0.17
    ulpt
    -0.17
     sugar
    -0.16
     Sugar
    -0.16
    lobal
    -0.16
    Cake
    -0.16
     Baker
    -0.16
     sugars
    -0.15
     snack
    -0.15
    dess
    -0.15
    POSITIVE LOGITS
     soup
    0.52
     broth
    0.46
     Soup
    0.46
    soup
    0.42
    Soup
    0.39
     stock
    0.37
     sou
    0.37
     Sou
    0.32
     Stock
    0.31
    湯
    0.30
    Act Density 0.089%

    No Known Activations