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

    Neuronpedia

    INDEX
    Explanations

    references to cooking, culinary skills, and food-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caffe
    -0.15
     thirsty
    -0.15
    jišť
    -0.14
     fiz
    -0.14
     conditioner
    -0.14
     Coffee
    -0.14
    ayo
    -0.14
     cigars
    -0.14
     Cotton
    -0.14
     tobacco
    -0.14
    POSITIVE LOGITS
     cooking
    0.40
     Cooking
    0.37
     cooks
    0.35
     cook
    0.35
     kitchen
    0.35
     kitchens
    0.35
    Cook
    0.34
     cookbook
    0.33
     culinary
    0.33
    Kitchen
    0.32
    Act Density 0.459%

    No Known Activations