INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Polynomial
    -0.09
    ajā
    -0.08
     Ist
    -0.08
    Polynomial
    -0.08
    STRUCTOR
    -0.07
     Uncomment
    -0.07
     Ih
    -0.07
    _pc
    -0.07
     Steuer
    -0.07
     Jump
    -0.07
    POSITIVE LOGITS
    dream
    0.11
    /night
    0.09
     mornings
    0.09
     יום
    0.09
     daytime
    0.09
     quotid
    0.08
    bells
    0.08
    grown
    0.08
     morning
    0.08
    -araw
    0.08
    Act Density 0.039%

    No Known Activations