INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Osborne
    -0.08
     swung
    -0.07
     King
    -0.07
     کاربرد
    -0.06
    apache
    -0.06
     ước
    -0.06
    (["
    -0.06
     =↵↵
    -0.06
    Congress
    -0.06
     ülke
    -0.06
    POSITIVE LOGITS
     detail
    0.13
    Detail
    0.12
     details
    0.12
    detail
    0.11
     detailing
    0.11
     Detail
    0.11
    _detail
    0.10
    DetailView
    0.10
    Details
    0.09
    -detail
    0.09
    Act Density 0.030%

    No Known Activations