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

    Neuronpedia

    INDEX
    Explanations

    ingredients or food-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to fresh ingredients in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.89
    uyomi
    -0.87
    ertodd
    -0.85
    hit
    -0.79
    xual
    -0.77
    arsity
    -0.75
    ysics
    -0.75
    orney
    -0.74
    én
    -0.74
    urches
    -0.73
    POSITIVE LOGITS
     vegetables
    0.98
     tomatoes
    0.98
     herbs
    0.96
     vegetable
    0.95
     foods
    0.94
     harvested
    0.89
     veggies
    0.88
     ingredients
    0.86
     imported
    0.85
     dairy
    0.85
    Act Density 0.155%

    No Known Activations