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

    Neuronpedia

    INDEX
    Explanations

    ingredients and preparation steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    specific cooking-related ingredients and preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.85
    ajo
    -0.74
    xual
    -0.74
    jump
    -0.72
    dq
    -0.72
    udic
    -0.72
    chairs
    -0.71
    arios
    -0.70
    esville
    -0.70
    iveness
    -0.69
    POSITIVE LOGITS
     vegetables
    1.00
     garlic
    0.99
     vegetable
    0.97
     ginger
    0.96
     strawberries
    0.96
     veggies
    0.93
     fruits
    0.92
     minced
    0.89
     coconut
    0.87
     bread
    0.86
    Act Density 0.088%

    No Known Activations