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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pomp
    -0.07
    挛
    -0.07
    signup
    -0.07
    حج
    -0.07
    ENU
    -0.07
    onest
    -0.07
     LICENSE
    -0.06
    仝
    -0.06
    мышл
    -0.06
     objection
    -0.06
    POSITIVE LOGITS
     الأه
    0.08
     audience
    0.08
     welcomed
    0.08
    Las
    0.07
     Gradient
    0.07
     habitat
    0.07
    Food
    0.07
     заказ
    0.07
    ﭐ
    0.07
    عام
    0.07
    Act Density 0.008%

    No Known Activations