INDEX
Explanations
mentions of the name "Scott."
New Auto-Interp
Negative Logits
calling
-0.17
Loc
-0.16
.scalablytyped
-0.16
дап
-0.15
cxx
-0.14
erties
-0.14
loc
-0.14
UBE
-0.14
headed
-0.14
apo
-0.14
POSITIVE LOGITS
sdale
0.42
ish
0.28
y
0.23
ie
0.20
enzie
0.19
i
0.19
astic
0.18
s
0.18
ISH
0.17
chia
0.17
Activations Density 0.004%