INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     begge
    0.62
     ambos
    0.59
     Beide
    0.57
     beide
    0.55
    两者
    0.54
     обоих
    0.54
     ಎರಡ
    0.53
     oba
    0.51
     બંને
    0.49
     keduanya
    0.48
    POSITIVE LOGITS
     three
    2.23
     तीनों
    2.20
    three
    2.05
     trois
    1.93
    Three
    1.92
    三个
    1.90
     Three
    1.86
     drei
    1.86
     trio
    1.85
     três
    1.81
    Act Density 0.517%

    No Known Activations