INDEX
Explanations
phrases indicating possession or existence in various contexts
New Auto-Interp
Negative Logits
no
-0.15
OnInit
-0.15
inho
-0.14
ilate
-0.14
only
-0.14
_already
-0.14
ander
-0.14
uelle
-0.14
una
-0.13
ichert
-0.13
POSITIVE LOGITS
indeed
0.18
occasionally
0.16
Indeed
0.15
SOME
0.15
however
0.15
698
0.15
inde
0.15
somewhat
0.15
iform
0.14
some
0.14
Activations Density 0.062%