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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     of
    -0.08
    免
    -0.08
     Take
    -0.07
     Any
    -0.07
     offset
    -0.07
    姻
    -0.07
    	type
    -0.07
     Wolf
    -0.07
     Sole
    -0.07
    慈
    -0.07
    POSITIVE LOGITS
    营养价值
    0.08
     criticized
    0.08
     criticism
    0.07
     deutsch
    0.07
    .println
    0.07
     때문에
    0.07
     חיפה
    0.07
     Persian
    0.07
     דיגיט
    0.07
     criticizing
    0.07
    Act Density 0.012%

    No Known Activations