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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lege
    -0.08
    现实中
    -0.08
    想起来
    -0.07
    塊
    -0.07
    Виде
    -0.07
    REN
    -0.07
     الخار
    -0.07
     buz
    -0.06
    有一点
    -0.06
    _three
    -0.06
    POSITIVE LOGITS
     screams
    0.07
     derives
    0.07
     throwError
    0.07
    تركيز
    0.07
     empowering
    0.06
     TIFF
    0.06
     enthusiastically
    0.06
    쑉
    0.06
    ilent
    0.06
    .foundation
    0.06
    Act Density 0.037%

    No Known Activations