INDEX
Explanations
instances of the verb "has" in various grammatical forms
New Auto-Interp
Negative Logits
sst
-0.18
anna
-0.15
adan
-0.14
à¥ģà¤
-0.14
oss
-0.14
forgot
-0.14
egend
-0.14
otor
-0.14
yc
-0.14
ervas
-0.14
POSITIVE LOGITS
been
0.34
been
0.26
become
0.21
since
0.19
its
0.19
Been
0.17
Been
0.17
already
0.17
now
0.16
sido
0.16
Activations Density 0.118%