INDEX
Explanations
the verb "is" and its various forms, indicating definitions or states of being
New Auto-Interp
Negative Logits
/trunk
-0.15
iji
-0.15
kö
-0.14
isp
-0.14
ajs
-0.14
ston
-0.14
soon
-0.14
inf
-0.13
odb
-0.13
aro
-0.13
POSITIVE LOGITS
nde
0.16
eldorf
0.15
нам
0.15
ActionController
0.15
ycz
0.15
ravel
0.14
.spi
0.14
ãĥĨãĥ«
0.14
newcom
0.14
neau
0.14
Activations Density 0.033%