INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -j
    -0.06
     isa
    -0.06
     fj
    -0.06
     MAK
    -0.06
     elk
    -0.06
    pin
    -0.06
     tik
    -0.06
    ัฒ
    -0.06
    -0.06
     tai
    -0.06
    POSITIVE LOGITS
     O
    0.35
    O
    0.17
    .O
    0.15
    ,O
    0.15
    -O
    0.13
    (O
    0.12
    	O
    0.12
    _O
    0.12
    'O
    0.11
    >O
    0.11
    Act Density 0.033%

    No Known Activations