INDEX
Explanations
first-person and second-person pronouns indicating personal involvement or experience
New Auto-Interp
Negative Logits
else
-0.16
anders
-0.15
urst
-0.15
caf
-0.14
759
-0.14
orks
-0.14
asso
-0.14
wards
-0.14
ساÙĨÛĮ
-0.14
erm
-0.13
POSITIVE LOGITS
onec
0.15
smarty
0.15
-pane
0.15
ÑĪиб
0.15
teil
0.14
CORE
0.14
anale
0.14
åī¯
0.14
myp
0.13
chance
0.13
Activations Density 0.212%