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

    Neuronpedia

    INDEX
    Explanations

    instructions for baking or cooking a recipe

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.74
     Cele
    -0.70
    awks
    -0.68
    ighth
    -0.64
     tattoos
    -0.64
     funer
    -0.64
    agra
    -0.63
    utics
    -0.63
     retirees
    -0.62
     Ost
    -0.61
    POSITIVE LOGITS
     blender
    0.94
     freezer
    0.92
     parchment
    0.86
     skillet
    0.83
     oven
    0.80
     Bake
    0.76
     preferably
    0.75
    safe
    0.74
    Prep
    0.73
    poon
    0.73
    Act Density 0.124%

    No Known Activations