INDEX
    Explanations

    actions related to public health measures and safety guidelines

    New Auto-Interp
    Negative Logits
     Privacy
    -0.15
    gio
    -0.14
    loon
    -0.14
    xDA
    -0.14
    adesh
    -0.14
    á»įt
    -0.14
    hor
    -0.14
    ì§
    -0.13
    oi
    -0.13
    Ìĥ
    -0.13
    POSITIVE LOGITS
     staying
    0.18
     familiar
    0.17
     everyone
    0.16
    ucer
    0.16
    Stay
    0.16
     stay
    0.15
     Stay
    0.15
    everyone
    0.15
     extra
    0.15
     behaviors
    0.15
    Act Density 0.100%

    No Known Activations