INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     KT
    -0.09
     tornando
    -0.08
     overhead
    -0.08
     тя
    -0.08
     hale
    -0.07
     teil
    -0.07
     Walters
    -0.07
     Kobe
    -0.07
     Shay
    -0.07
    KT
    -0.07
    POSITIVE LOGITS
    ুগ
    0.08
    .IF
    0.08
     figuring
    0.08
    0.08
     Sight
    0.08
    Sight
    0.07
    (if
    0.07
    SUN
    0.07
    Genome
    0.07
     squid
    0.07
    Act Density 0.003%

    No Known Activations