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

    Neuronpedia

    INDEX
    Explanations

    ingredients and instructions for baking recipes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    dq
    -0.76
     fences
    -0.71
    ¥µ
    -0.70
     exhibitions
    -0.68
    rists
    -0.67
    uctions
    -0.66
    eatures
    -0.64
    meet
    -0.62
    qv
    -0.61
    fest
    -0.61
    POSITIVE LOGITS
     extract
    0.85
    Ingredients
    0.82
     Instructions
    0.81
    poons
    0.80
     Extract
    0.79
     diced
    0.76
     powder
    0.74
     (~
    0.73
     scramble
    0.73
     Ingredients
    0.72
    Act Density 0.071%

    No Known Activations