INDEX
Explanations
the verb "am" in various contexts within the text
New Auto-Interp
Negative Logits
amina
-0.17
agt
-0.16
ama
-0.16
an
-0.15
AMA
-0.15
splash
-0.15
legate
-0.14
ocket
-0.14
ampa
-0.14
ussion
-0.14
POSITIVE LOGITS
.pretty
0.16
iny
0.16
ft
0.15
žÃŃ
0.15
wa
0.14
resse
0.14
CDs
0.14
é«Ķ
0.14
ollo
0.13
olare
0.13
Activations Density 0.048%