INDEX
Explanations
phrases related to social justice and collective responsibility
New Auto-Interp
Negative Logits
ode
-0.16
ToPoint
-0.14
adden
-0.14
Federal
-0.14
alar
-0.14
ostel
-0.14
aron
-0.13
ene
-0.13
Bene
-0.13
730
-0.13
POSITIVE LOGITS
antom
0.14
egasus
0.14
inja
0.14
Blasio
0.13
oller
0.13
gons
0.13
inclu
0.13
cpp
0.13
563
0.13
itta
0.13
Activations Density 0.296%