INDEX
Explanations
references to the construction industry and related entities
New Auto-Interp
Negative Logits
nings
-0.18
ASM
-0.15
ire
-0.15
μι
-0.15
uro
-0.15
nten
-0.15
raz
-0.15
opi
-0.14
rost
-0.14
iti
-0.14
POSITIVE LOGITS
earer
0.15
liž
0.15
APS
0.15
ãĥ³ãĥĨãĤ£
0.15
enko
0.14
meni
0.14
anford
0.14
ilarity
0.14
lady
0.14
eldorf
0.14
Activations Density 0.015%