INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cav
    -0.07
    	assertThat
    -0.07
    UILDER
    -0.07
    อดภ
    -0.06
    ινή
    -0.06
     Appeals
    -0.06
    clamation
    -0.06
     بندی
    -0.06
     ils
    -0.06
     disple
    -0.06
    POSITIVE LOGITS
     Buy
    0.08
     dio
    0.08
    ød
    0.06
     expo
    0.06
     expos
    0.06
     polít
    0.06
    hy
    0.06
    ':"
    0.06
    _matches
    0.06
     redevelopment
    0.06
    Act Density 0.019%

    No Known Activations