INDEX
Explanations
phrases related to social and political activism, particularly concerning LGBTQ+ issues
New Auto-Interp
Negative Logits
RenderAtEndOf
-0.69
AddTagHelper
-0.61
ſelf
-0.60
שוליים
-0.58
ագրություններ
-0.57
المناصب
-0.56
ロウィン
-0.55
참고
-0.55
مشين
-0.53
ParallelGroup
-0.52
POSITIVE LOGITS
these
0.44
also
0.44
これに
0.38
isso
0.36
そういう
0.36
therewith
0.36
そう
0.36
それを
0.35
them
0.35
however
0.35
Activations Density 0.784%