INDEX
    Explanations

    Describing people

    New Auto-Interp
    Negative Logits
    ğine
    -0.06
     PS
    -0.06
     Inform
    -0.06
     chan
    -0.06
    Bang
    -0.06
    _jButton
    -0.05
    Event
    -0.05
    [::-
    -0.05
     :↵↵↵↵
    -0.05
    คน
    -0.05
    POSITIVE LOGITS
    در
    0.07
     REL
    0.07
     Counseling
    0.07
    .books
    0.07
     ؛
    0.07
    งเศส
    0.07
    _tol
    0.07
     walker
    0.06
    (od
    0.06
    /v
    0.06
    Act Density 0.035%

    No Known Activations