INDEX
Explanations
references to fossil fuels and related energy resources
New Auto-Interp
Negative Logits
ogh
-0.17
314
-0.16
pert
-0.15
tandem
-0.14
marks
-0.14
Radical
-0.14
exc
-0.14
بع
-0.14
iche
-0.14
ema
-0.14
POSITIVE LOGITS
deÅŁ
0.15
bekl
0.15
agua
0.15
baiser
0.15
ldr
0.15
šak
0.14
izr
0.14
-transitional
0.14
ODULE
0.14
.gdx
0.14
Activations Density 0.010%