INDEX
Explanations
references to pipelines, particularly related to environmental concerns and local governance
New Auto-Interp
Negative Logits
alez
-0.15
unga
-0.15
leet
-0.15
ILLE
-0.14
ille
-0.14
rale
-0.14
agnost
-0.14
rank
-0.14
irc
-0.14
alted
-0.13
POSITIVE LOGITS
pil
0.36
Pil
0.34
grim
0.26
oted
0.22
oting
0.21
beam
0.20
pilgr
0.20
PIL
0.19
atus
0.18
bara
0.17
Activations Density 0.008%