INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    冷静
    0.45
     deont
    0.43
     फ्रैक्शन
    0.40
    票房
    0.39
     الشيطان
    0.38
    यर्स
    0.38
     интерфей
    0.38
     উত্তেজনা
    0.38
    0.38
    gpt
    0.37
    POSITIVE LOGITS
     plants
    2.11
    植物
    1.95
     растения
    1.91
     vegetation
    1.84
     tanaman
    1.81
     flowers
    1.77
     Plants
    1.77
    Plants
    1.76
     roślin
    1.73
     plantas
    1.73
    Act Density 0.116%

    No Known Activations