INDEX
Explanations
references to global issues such as climate change and globalization
New Auto-Interp
Negative Logits
ORY
-0.17
ikel
-0.17
erman
-0.16
seau
-0.16
jas
-0.16
ards
-0.15
iw
-0.15
sse
-0.15
awai
-0.15
ourke
-0.15
POSITIVE LOGITS
/local
0.32
warming
0.28
ToLocal
0.25
/global
0.24
izing
0.24
isation
0.24
-local
0.23
ized
0.23
ization
0.22
ised
0.21
Activations Density 0.025%