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

    Neuronpedia

    INDEX
    Explanations

    ingredients and measurements in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredient names and their measurements in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .""
    -0.74
    itism
    -0.73
    ',"
    -0.67
    enegger
    -0.67
    '."
    -0.66
    !'"
    -0.64
    dq
    -0.63
    .'"
    -0.62
    ERY
    -0.59
    SpaceEngineers
    -0.59
    POSITIVE LOGITS
     Instructions
    1.30
     Directions
    1.28
     Optional
    0.97
    optional
    0.94
     finely
    0.91
     chopped
    0.86
     diced
    0.84
     optional
    0.83
     softened
    0.83
     ½
    0.82
    Act Density 0.105%

    No Known Activations