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

    Neuronpedia

    INDEX
    Explanations

    baking ingredients and instructions

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and quantities in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     careers
    -0.82
     responding
    -0.79
     evidenced
    -0.78
     patrols
    -0.78
     athlet
    -0.77
     coordinated
    -0.77
     fielded
    -0.77
     evolved
    -0.77
     featured
    -0.77
     tours
    -0.76
    POSITIVE LOGITS
    Instruct
    1.54
    Optional
    1.48
    Ingredients
    1.45
    ½
    1.44
    Method
    1.44
    Direct
    1.43
    Salt
    1.40
    Recipe
    1.38
    METHOD
    1.32
    Heat
    1.32
    Act Density 0.033%

    No Known Activations