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

    Neuronpedia

    INDEX
    Explanations

    references to dairy products and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.90
    i
    -0.79
     Montero
    -0.73
    üsü
    -0.64
    い
    -0.63
     determined
    -0.63
    jes
    -0.62
    жу
    -0.62
     red
    -0.62
    ي
    -0.61
    POSITIVE LOGITS
     Milk
    1.52
     Cream
    1.48
     CREAM
    1.45
     MILK
    1.45
    Milk
    1.42
     milk
    1.42
     cream
    1.36
    Cream
    1.31
    cream
    1.28
    milk
    1.24
    Act Density 0.085%

    No Known Activations