INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     measurements
    -0.07
     observe
    -0.07
    _allocate
    -0.07
     scaffold
    -0.07
    observe
    -0.07
    .Collections
    -0.07
    -0.07
     body's
    -0.07
     defence
    -0.07
     surrounding
    -0.07
    POSITIVE LOGITS
     이름
    0.11
    名称
    0.10
    类别
    0.10
     종류
    0.09
    0.09
     제목
    0.09
    이블
    0.09
    마다
    0.09
    类型
    0.09
     دسته
    0.09
    Act Density 0.023%

    No Known Activations