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

    Neuronpedia

    INDEX
    Explanations

    ingredients and cooking instructions in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and cooking measurements in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.72
     Yards
    -0.68
    ICLE
    -0.68
     careers
    -0.67
    GoldMagikarp
    -0.65
     WATCHED
    -0.64
     skelet
    -0.64
     Intellectual
    -0.64
    eport
    -0.63
    WT
    -0.63
    POSITIVE LOGITS
     flakes
    0.99
     mixture
    0.93
     powder
    0.92
     mustard
    0.92
     ingred
    0.90
     vinegar
    0.89
     ingredients
    0.88
     baking
    0.88
     blend
    0.86
     sauce
    0.86
    Act Density 0.129%

    No Known Activations