INDEX
    Explanations

    ask, act, set, number, test

    New Auto-Interp
    Negative Logits
     Казіно
    0.50
    ¹.
    0.50
     ».
    0.48
    ®.
    0.47
    0.47
    ².
    0.47
    ³.
    0.47
    **:
    0.46
     }}$.
    0.46
    0.45
    POSITIVE LOGITS
    0.66
       
    0.60
        
    0.44
            
    0.41
    	
    0.41
    einander
    0.39
    %
    0.39
    ,$
    0.38
    _
    0.38
    /
    0.36
    Act Density 0.014%

    No Known Activations