INDEX
Explanations
references to social and political issues in various contexts
New Auto-Interp
Negative Logits
abilit
-0.17
iquer
-0.15
kå
-0.14
iPad
-0.14
createState
-0.14
ipc
-0.14
FTA
-0.14
ibling
-0.14
UnitTest
-0.14
damer
-0.13
POSITIVE LOGITS
boycott
0.23
protest
0.19
decision
0.19
boyc
0.17
sensitivity
0.17
protests
0.16
cez
0.16
decision
0.16
Decision
0.15
protesting
0.15
Activations Density 0.120%