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

    Neuronpedia

    INDEX
    Explanations

    references to kitchen-related spaces within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Greif
    -0.47
     Numerade
    -0.45
    Vidu
    -0.45
     Blake
    -0.43
     {*}
    -0.42
    隈
    -0.42
     SCORE
    -0.42
     Bảo
    -0.41
     Correa
    -0.41
     pot
    -0.41
    POSITIVE LOGITS
    Kitchen
    1.08
    kitchen
    1.07
     kitchen
    1.03
     Kitchen
    1.02
     KITCHEN
    0.95
    ITCHEN
    0.93
     kitchenette
    0.81
     kitchens
    0.80
     Kitchens
    0.80
     dapur
    0.68
    Act Density 0.020%

    No Known Activations