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

    Neuronpedia

    INDEX
    Explanations

    ingredients and directions in a cooking recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and quantities in cooking instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.76
     experien
    -0.74
    isphere
    -0.70
    emort
    -0.70
     Inquiry
    -0.67
     guiActiveUn
    -0.64
     tremend
    -0.64
     FOIA
    -0.64
    BILL
    -0.64
     Facility
    -0.64
    POSITIVE LOGITS
     vinegar
    0.97
     pulp
    0.95
     baking
    0.89
     cinnamon
    0.88
     salt
    0.87
     citrus
    0.87
     optionally
    0.87
     cellul
    0.85
     vitamins
    0.85
     spices
    0.85
    Act Density 0.344%

    No Known Activations