INDEX
Explanations
mentions of specific individuals and their contextual significance in narratives
New Auto-Interp
Negative Logits
obi
-0.18
KeyId
-0.15
lund
-0.15
illo
-0.15
indeed
-0.14
Beaver
-0.14
okus
-0.14
Balt
-0.14
LU
-0.14
obec
-0.14
POSITIVE LOGITS
vÄĽt
0.17
olls
0.15
azo
0.15
Pow
0.14
avax
0.14
uxt
0.14
olib
0.14
STILL
0.14
ERSION
0.14
ovsky
0.14
Activations Density 0.134%