INDEX
    Explanations

    mathematical equations

    New Auto-Interp
    Negative Logits
    -0.09
     шо
    -0.09
     coach
    -0.08
    zos
    -0.07
     Ziel
    -0.07
    	counter
    -0.07
    	curr
    -0.07
    loh
    -0.07
    ppy
    -0.07
     counter
    -0.07
    POSITIVE LOGITS
    _like
    0.09
    ค่ะ
    0.09
     konsa
    0.09
    니까
    0.08
     altså
    0.08
     alltså
    0.08
    Obrig
    0.08
     SUS
    0.08
    Like
    0.07
    ).^
    0.07
    Act Density 0.535%

    No Known Activations