INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -
    1.45
    	
    1.15
                
    1.08
    бычно
    1.07
    1
    1.05
    <0x80>
    1.03
    -<
    1.02
                    
    1.00
    					
    1.00
    ৬৫
    0.99
    POSITIVE LOGITS
    ul
    1.17
    ان
    0.94
    ۔
    0.93
    io
    0.93
    ون
    0.93
    ید
    0.93
    ip
    0.89
    od
    0.89
    ير
    0.88
    ره
    0.88
    Act Density 0.023%

    No Known Activations