INDEX
Explanations
phrases related to human rights and healthcare rights
New Auto-Interp
Negative Logits
ocre
-0.18
eyh
-0.15
æĤŁ
-0.15
hek
-0.15
æº
-0.14
-rights
-0.14
ãng
-0.14
acker
-0.14
年代
-0.14
arium
-0.14
POSITIVE LOGITS
privacy
0.27
due
0.21
privacy
0.21
Privacy
0.21
freely
0.21
Due
0.20
Privacy
0.19
freedom
0.19
free
0.19
expression
0.18
Activations Density 0.043%