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

    Neuronpedia

    INDEX
    Explanations

    references to the process of cooking food thoroughly or at high heat

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     kitchen
    -0.66
     Kitchen
    -0.57
     dish
    -0.56
    SequentialGroup
    -0.54
    kitchen
    -0.52
     despe
    -0.51
    Kitchen
    -0.51
    tabular
    -0.50
     Cook
    -0.50
     Staf
    -0.49
    POSITIVE LOGITS
     cooked
    2.73
    cooked
    2.58
     Cooked
    2.34
    baked
    0.87
     baked
    0.80
     brewed
    0.80
    IndentedString
    0.79
    ArrowToggle
    0.76
     Baked
    0.72
    出版年
    0.71
    Act Density 0.002%

    No Known Activations