INDEX
Explanations
verbs indicating existence or state of being
New Auto-Interp
Negative Logits
previously
-0.17
обов
-0.15
ape
-0.14
arc
-0.14
ÙģØª
-0.14
suce
-0.14
verted
-0.14
Sext
-0.13
unde
-0.13
appendString
-0.13
POSITIVE LOGITS
shown
0.27
seen
0.22
pictured
0.22
shown
0.20
back
0.19
hereby
0.19
pictured
0.19
Shown
0.18
set
0.18
being
0.17
Activations Density 0.057%