INDEX
Explanations
references to awareness and celebration months or weeks focused on social issues and cultural identity
New Auto-Interp
Negative Logits
ãĥ³ãĥĪ
-0.17
eyer
-0.15
éĢĢ
-0.14
's
-0.14
TL
-0.14
ofi
-0.14
éĢĢåĩº
-0.14
,
-0.14
æĿ
-0.14
agua
-0.13
POSITIVE LOGITS
cott
0.16
bson
0.16
orget
0.15
áct
0.15
avaÅŁ
0.15
ấm
0.15
поÑĪ
0.15
cpy
0.14
законом
0.14
hra
0.14
Activations Density 0.038%