INDEX
Explanations
mentions of the word "actual" and its variants in various contexts
New Auto-Interp
Negative Logits
edor
-0.16
kle
-0.16
esp
-0.14
.COMP
-0.14
iesel
-0.14
Malk
-0.14
spb
-0.14
etik
-0.13
atz
-0.13
eler
-0.13
POSITIVE LOGITS
ités
0.21
actual
0.19
mente
0.19
Actual
0.18
physical
0.17
Actual
0.17
igned
0.17
actual
0.16
leh
0.15
andon
0.15
Activations Density 0.058%