INDEX
Explanations
phrases related to expressing support for various causes or groups
instances of support related to political or social causes
New Auto-Interp
Negative Logits
ĸļ
-0.94
ãĤ¼ãĤ¦ãĤ¹
-0.81
partName
-0.69
fry
-0.66
ngth
-0.64
ILCS
-0.63
\<
-0.62
ashtra
-0.62
};
-0.61
WARNING
-0.61
POSITIVE LOGITS
legalizing
0.81
equality
0.79
separat
0.78
incumb
0.76
independence
0.76
stricter
0.76
preserving
0.74
initiatives
0.74
repealing
0.73
reforming
0.73
Activations Density 0.137%