INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     сним
    0.38
     tabela
    0.38
     rude
    0.37
     nuit
    0.37
     kijk
    0.37
     arbe
    0.36
     prêts
    0.35
     prête
    0.35
     abundante
    0.35
     kancel
    0.35
    POSITIVE LOGITS
     Patterns
    0.82
     pattern
    0.79
    patterns
    0.79
     patterns
    0.78
    pattern
    0.76
    Patterns
    0.75
     Pattern
    0.74
     패턴
    0.74
    PATTERN
    0.70
     पैटर्न
    0.68
    Act Density 0.004%

    No Known Activations