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

    Neuronpedia

    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking and food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dx
    -0.69
    kat
    -0.68
    anmar
    -0.65
     KP
    -0.63
    href
    -0.63
     categ
    -0.62
    daq
    -0.62
     dx
    -0.61
    xy
    -0.60
    kus
    -0.60
    POSITIVE LOGITS
     Serve
    1.10
     garn
    1.10
    riger
    1.01
     Serving
    0.93
    Optional
    0.91
    Remove
    0.87
     serve
    0.86
     Garn
    0.86
    optional
    0.85
    Recipe
    0.84
    Act Density 0.109%

    No Known Activations