INDEX
    Explanations

    con [quality/attribute]

    New Auto-Interp
    Negative Logits
     Sukh
    0.47
     그렇게
    0.45
     Szym
    0.43
     resh
    0.42
    áneamente
    0.42
    wärts
    0.41
     salami
    0.41
     расстоянии
    0.40
     Mou
    0.40
     Aden
    0.40
    POSITIVE LOGITS
     enorme
    0.78
     grande
    0.68
     forte
    0.64
     considerable
    0.60
     fuerte
    0.59
     enormes
    0.57
     carácter
    0.57
     enormous
    0.55
     ampla
    0.55
     particular
    0.55
    Act Density 0.018%

    No Known Activations