INDEX
Explanations
mention of the word "Montgomery"
New Auto-Interp
Negative Logits
urement
-0.16
peg
-0.15
sg
-0.15
leh
-0.15
hala
-0.15
Huss
-0.15
indr
-0.14
Garrison
-0.13
ventas
-0.13
Gree
-0.13
POSITIVE LOGITS
shire
0.17
ilst
0.15
sar
0.15
ourn
0.14
serrat
0.14
tainment
0.14
énom
0.14
iegel
0.14
emic
0.14
anje
0.14
Activations Density 0.001%