INDEX
Explanations
the presence of the term "Kruger" in various contexts
New Auto-Interp
Negative Logits
rosse
-0.16
amarin
-0.15
ariat
-0.15
ire
-0.15
fos
-0.15
obus
-0.15
СÑĢед
-0.14
overs
-0.14
oucher
-0.14
ookie
-0.14
POSITIVE LOGITS
ystal
0.22
utch
0.16
ddit
0.16
holm
0.16
ude
0.15
ishi
0.15
yst
0.15
uger
0.15
stin
0.15
akter
0.15
Activations Density 0.010%