INDEX
Explanations
references to COVID-19 and its impact
New Auto-Interp
Negative Logits
guard
-0.17
743
-0.16
109
-0.15
ing
-0.15
aine
-0.15
404
-0.15
202
-0.14
list
-0.14
206
-0.14
293
-0.14
POSITIVE LOGITS
â̳
0.45
â̲
0.41
s
0.40
ï¸ı
0.33
/-
0.24
-й
0.24
sak
0.23
-го
0.22
sheets
0.22
sand
0.21
Activations Density 0.299%