INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    akuru
    -0.08
     DWORD
    -0.07
     mafia
    -0.07
     certeza
    -0.07
     AIDS
    -0.07
     Nar
    -0.07
     acres
    -0.07
     }>
    -0.07
     проц
    -0.07
     fright
    -0.07
    POSITIVE LOGITS
     minimalist
    0.21
     simplicité
    0.16
     simplicity
    0.15
     understated
    0.13
    Elegant
    0.13
     eenvoud
    0.13
     elegance
    0.13
     elegant
    0.13
     sederhana
    0.13
     Einfach
    0.13
    Act Density 0.127%

    No Known Activations