INDEX
Explanations
instances of the word "since" emphasizing time or duration
New Auto-Interp
Negative Logits
ingt
-0.20
немÑĥ
-0.15
krv
-0.15
nox
-0.15
_RCC
-0.15
geois
-0.14
locker
-0.14
ожд
-0.14
.radioButton
-0.14
liner
-0.13
POSITIVE LOGITS
inception
0.23
they
0.22
its
0.21
before
0.20
we
0.20
childhood
0.18
being
0.18
last
0.17
becoming
0.17
then
0.17
Activations Density 0.042%