INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     zor
    -0.08
     бор
    -0.08
     zomaar
    -0.08
     ding
    -0.08
     radically
    -0.07
    #ifndef
    -0.07
     visibly
    -0.07
     vain
    -0.07
     gav
    -0.07
     apolog
    -0.07
    POSITIVE LOGITS
     later
    0.13
     nanti
    0.12
    Later
    0.11
     später
    0.11
    later
    0.11
     senere
    0.11
     لاح
    0.11
     senare
    0.10
     позже
    0.10
     Later
    0.10
    Act Density 0.026%

    No Known Activations