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

    Neuronpedia

    INDEX
    Explanations

    food items and their preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omiast
    -0.45
    Tracce
    -0.43
    AnchorStyles
    -0.41
     Pozna
    -0.40
    vician
    -0.39
     almend
    -0.39
     canela
    -0.38
     Joao
    -0.38
    tonode
    -0.38
     Conſ
    -0.37
    POSITIVE LOGITS
     broccoli
    0.90
     cauliflower
    0.81
     vegetables
    0.81
     cabbage
    0.80
     veggies
    0.79
     kale
    0.79
     greens
    0.77
     lettuce
    0.76
     zucchini
    0.75
     carrots
    0.75
    Act Density 0.245%

    No Known Activations