INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     zakoń
    1.04
    ształ
    1.02
     Abbiamo
    1.00
     nekoliko
    1.00
    irken
    0.98
    ័រ
    0.98
    к
    0.97
     σχέ
    0.96
     Dopo
    0.96
     Comando
    0.94
    POSITIVE LOGITS
    𝑡
    0.98
     alcohol
    0.95
    friction
    0.93
    rugu
    0.92
    hoea
    0.89
    answer
    0.88
    single
    0.87
    assay
    0.87
     Alcohol
    0.86
     алкого
    0.86
    Act Density 0.001%

    No Known Activations