INDEX
Explanations
references to global issues and crises
New Auto-Interp
Negative Logits
åħ¨åĽ½
-0.19
GLOBALS
-0.18
گاÙĩ
-0.17
Jako
-0.17
erman
-0.16
nationwide
-0.16
elor
-0.16
ORY
-0.16
sse
-0.15
chie
-0.15
POSITIVE LOGITS
/local
0.34
warming
0.32
ized
0.32
isation
0.28
ised
0.27
/reg
0.26
-local
0.26
izing
0.26
/world
0.25
ization
0.24
Activations Density 0.027%