INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    '
    0.79
        
    0.77
    :
    0.71
     '
    0.70
     \
    0.61
    (
    0.60
    \
    0.60
     give
    0.58
    $\
    0.58
    t
    0.58
    POSITIVE LOGITS
    睡觉
    0.89
     dormir
    0.87
    💤
    0.85
     ночь
    0.83
    😴
    0.83
     خواب
    0.82
     ngủ
    0.81
     नींद
    0.80
     noches
    0.80
    0.79
    Act Density 0.039%

    No Known Activations