INDEX
    Explanations

    comparative adjectives

    New Auto-Interp
    Negative Logits
    重大
    -0.07
    .translatesAutoresizingMaskIntoConstraints
    -0.07
    convert
    -0.07
    ߠ
    -0.07
     Describe
    -0.06
    .experimental
    -0.06
    -0.06
     prescribe
    -0.06
     develops
    -0.06
     Montreal
    -0.06
    POSITIVE LOGITS
    0.08
     thanking
    0.07
    雅黑
    0.07
     rubbed
    0.07
     tq
    0.07
     tm
    0.07
    给人一种
    0.06
        		
    0.06
    resher
    0.06
    -picker
    0.06
    Act Density 0.094%

    No Known Activations