INDEX
Explanations
mask mandates and requirements
New Auto-Interp
Negative Logits
wearing
0.79
Wearing
0.77
穿着
0.75
Wearing
0.73
wearing
0.71
wears
0.71
wearer
0.64
wore
0.60
indoss
0.59
पहन
0.55
POSITIVE LOGITS
mask
0.59
covering
0.55
face
0.52
mouth
0.50
masks
0.50
Covering
0.50
mask
0.48
Mask
0.47
covering
0.47
マスク
0.47
Activations Density 0.007%