INDEX
Explanations
calls to action regarding political issues and social concerns
New Auto-Interp
Negative Logits
npos
-0.16
FindObject
-0.16
akhir
-0.15
aepernick
-0.15
ennen
-0.14
ipment
-0.14
igan
-0.14
peq
-0.14
itbart
-0.14
nio
-0.14
POSITIVE LOGITS
wing
0.17
wing
0.16
Messaging
0.16
win
0.15
unity
0.15
igli
0.15
exit
0.14
intra
0.14
Messaging
0.14
aperture
0.14
Activations Density 0.076%