INDEX
Explanations
references to socioeconomic disparities and conditions
New Auto-Interp
Negative Logits
;set
-0.15
ëŀĢ
-0.15
BOOLE
-0.15
NameValuePair
-0.15
-cn
-0.14
sans
-0.14
–↵↵
-0.14
íĮĶ
-0.14
bekl
-0.14
—↵↵
-0.13
POSITIVE LOGITS
âĢŀ
0.26
âĢŀ
0.21
nice
0.21
«
0.20
few
0.19
splitted
0.18
couple
0.17
)))
0.17
))
0.17
funny
0.17
Activations Density 0.755%