INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     preferably
    0.66
     preferred
    0.65
    0.64
     usually
    0.64
     significance
    0.64
    inyin
    0.63
     furiously
    0.63
     Preferably
    0.62
     frequently
    0.62
     often
    0.61
    POSITIVE LOGITS
     меж
    0.71
    Copy
    0.70
     proceso
    0.68
     Blast
    0.67
     Quelle
    0.66
     သူ့
    0.66
     لدى
    0.66
     inter
    0.65
    Sight
    0.65
    ರೋ
    0.65
    Act Density 0.025%

    No Known Activations