INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     spite
    -0.08
    .NoArgsConstructor
    -0.08
    -0.07
     Pit
    -0.07
    -0.07
     besides
    -0.07
    Despite
    -0.06
     GDK
    -0.06
     scent
    -0.06
    -0.06
    POSITIVE LOGITS
    نتج
    0.07
    >\
    0.07
    bel
    0.07
    0.07
    -start
    0.07
    anship
    0.07
     Imported
    0.06
    _open
    0.06
    0.06
    面白
    0.06
    Act Density 0.013%

    No Known Activations