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

    ingredients and measurements commonly used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pett
    -0.72
    76561
    -0.70
    geries
    -0.69
    Ly
    -0.68
    ORPG
    -0.65
     Yards
    -0.65
     Poster
    -0.64
    nen
    -0.64
    bred
    -0.63
    pict
    -0.63
    POSITIVE LOGITS
     flakes
    0.88
     sauce
    0.82
     mixture
    0.79
     paste
    0.74
     sweetness
    0.73
     pinch
    0.73
     slur
    0.72
     Sauce
    0.71
     wrap
    0.71
     cloves
    0.71
    Act Density 0.125%

    No Known Activations