INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     touchdowns
    -0.06
    .Space
    -0.06
     oppressed
    -0.06
    istence
    -0.06
     rims
    -0.06
     physiological
    -0.06
    .asm
    -0.06
    	Texture
    -0.06
     polyester
    -0.06
     agreement
    -0.06
    POSITIVE LOGITS
     PART
    0.07
    δόν
    0.07
    Θ
    0.07
     MART
    0.07
    .commit
    0.06
     вообще
    0.06
     cookies
    0.06
    _PTR
    0.06
     often
    0.06
     inexperienced
    0.06
    Act Density 0.021%

    No Known Activations