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

    Neuronpedia

    INDEX
    Explanations

    ingredients and recipes for cooking

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and quantities typically used in cooking recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Student
    -0.70
     seism
    -0.68
    href
    -0.65
     Standing
    -0.64
     Employees
    -0.63
    ¥ŀ
    -0.62
     Geh
    -0.62
     Galile
    -0.61
    Veh
    -0.61
     polyg
    -0.60
    POSITIVE LOGITS
    nut
    1.02
    Ingredients
    0.98
    nuts
    0.96
     salad
    0.94
     conco
    0.93
     soup
    0.91
     flakes
    0.89
     sauce
    0.89
     ingredients
    0.89
     vinegar
    0.88
    Act Density 0.339%

    No Known Activations