INDEX
    Explanations

    prolonged sitting

    New Auto-Interp
    Negative Logits
     Dante
    -0.08
     Nis
    -0.08
     Marcus
    -0.08
    公安
    -0.07
     dommages
    -0.07
     Zert
    -0.07
     Kritik
    -0.07
     Curr
    -0.07
     Kanal
    -0.07
     cửa
    -0.07
    POSITIVE LOGITS
     sedent
    0.15
     बैठे
    0.10
     stagnant
    0.10
    allon
    0.09
     smoking
    0.08
    办公
    0.08
     сид
    0.08
     seated
    0.08
     legumes
    0.08
    _idle
    0.08
    Act Density 0.013%

    No Known Activations