INDEX
Explanations
the phrase "there is" in various contexts
New Auto-Interp
Negative Logits
omain
-0.15
agit
-0.14
.openConnection
-0.14
žel
-0.14
_UNUSED
-0.14
ober
-0.14
_MISC
-0.14
Č↵
-0.14
UED
-0.13
luž
-0.13
POSITIVE LOGITS
no
0.31
NO
0.25
No
0.23
.no
0.23
no
0.23
geen
0.21
,no
0.20
-no
0.19
keine
0.19
nothing
0.19
Activations Density 0.050%