INDEX
Explanations
instances of the word "actually" and variations of implies or indicates its use in context
New Auto-Interp
Negative Logits
stras
-0.19
esh
-0.18
rous
-0.16
ë¬
-0.16
fang
-0.15
iš
-0.14
est
-0.14
542
-0.14
edly
-0.14
eler
-0.14
POSITIVE LOGITS
-ÑĤаки
0.15
Thrones
0.15
mente
0.15
áli
0.15
worse
0.14
uated
0.14
ronym
0.14
ENU
0.14
quite
0.14
797
0.13
Activations Density 0.061%