INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     myſelf
    -1.09
     themſelves
    -1.07
     poffe
    -1.07
     poffible
    -1.07
     Jefus
    -1.06
     uſ
    -1.05
     itſelf
    -1.05
     purpoſe
    -1.03
     uſed
    -1.03
     fubject
    -1.03
    POSITIVE LOGITS
     незавершена
    0.45
     numbers
    0.43
     track
    0.42
     coi
    0.42
     rates
    0.40
     principes
    0.40
     prom
    0.39
     ch
    0.39
     pro
    0.39
     qual
    0.38
    Act Density 1.064%

    No Known Activations