INDEX
    Explanations

    synonymous

    New Auto-Interp
    Negative Logits
     démocratie
    -0.69
     fenomeno
    -0.68
     phénomènes
    -0.66
    Something
    -0.65
    something
    -0.65
     sesuatu
    -0.65
     qualcosa
    -0.65
     écl
    -0.62
     somethin
    -0.61
    Искәрмәләр
    -0.61
    POSITIVE LOGITS
     للتو
    0.58
    ftagPool
    0.50
     turned
    0.48
    GEBURTSDATUM
    0.48
     from
    0.46
    import
    0.45
     right
    0.44
     ro
    0.43
     novel
    0.43
    du
    0.43
    Act Density 0.023%

    No Known Activations