INDEX
Explanations
occurrences of the word "ever" in various contexts
New Auto-Interp
Negative Logits
erus
-0.18
OOT
-0.17
oot
-0.17
ÏĢον
-0.15
êu
-0.15
ronics
-0.14
morals
-0.14
exter
-0.14
eer
-0.14
393
-0.14
POSITIVE LOGITS
urse
0.15
ĴĪ
0.15
-ending
0.15
doch
0.15
umann
0.15
occo
0.14
adium
0.14
plate
0.14
celib
0.14
mind
0.14
Activations Density 0.012%