INDEX
Explanations
the infinitive form of verbs, particularly "to" followed by a verb
New Auto-Interp
Negative Logits
icina
-0.16
ÙĨØ´
-0.15
Bust
-0.15
uj
-0.14
ish
-0.14
PropertyDescriptor
-0.14
aban
-0.14
Sh
-0.14
now
-0.13
aff
-0.13
POSITIVE LOGITS
ihar
0.16
ãĤ«ãĥ¼
0.15
>NN
0.15
.scalablytyped
0.15
slaught
0.15
ellan
0.14
ekim
0.14
OMEM
0.14
.PLL
0.14
ÑĢави
0.14
Activations Density 0.010%