INDEX
Explanations
instances of physical injury or distress
New Auto-Interp
Negative Logits
illez
-0.17
either
-0.15
plus
-0.14
PLUS
-0.13
during
-0.13
onas
-0.13
qd
-0.13
ëĺIJëĬĶ
-0.13
nor
-0.13
throughout
-0.13
POSITIVE LOGITS
while
0.19
while
0.18
ancybox
0.17
whilst
0.17
mentre
0.17
expecting
0.17
expect
0.16
WHILE
0.15
mientras
0.15
prepar
0.15
Activations Density 0.520%