INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     arcu
    -0.08
    -town
    -0.08
    290
    -0.08
    invest
    -0.07
     Er
    -0.07
     Scholar
    -0.07
     čl
    -0.07
     ergo
    -0.07
     Town
    -0.07
    Town
    -0.07
    POSITIVE LOGITS
    yeen
    0.08
    ίνει
    0.08
    ятся
    0.08
     beide
    0.08
     ifade
    0.08
     ced
    0.08
     harus
    0.08
     einmal
    0.08
    ementara
    0.08
    ial
    0.08
    Act Density 0.010%

    No Known Activations