INDEX
    Explanations

    mathematical notation and symbols

    New Auto-Interp
    Negative Logits
     collectivités
    -0.45
     near
    -0.44
     petites
    -0.41
     viktigt
    -0.41
     region
    -0.40
     outer
    -0.40
     oberen
    -0.39
     area
    -0.38
     Near
    -0.38
     pet
    -0.38
    POSITIVE LOGITS
    )$
    2.25
    ]$
    1.45
    \}$
    1.44
     )$
    1.41
    )]$
    1.30
    )$}
    1.28
    })$
    1.27
    %)$
    1.24
    +)$
    1.22
    ))$
    1.21
    Act Density 0.207%

    No Known Activations