INDEX
Explanations
mentions of the name "Boris" and variations of it in different contexts
New Auto-Interp
Negative Logits
m
-0.15
llum
-0.15
tel
-0.15
ed
-0.15
tell
-0.14
.TO
-0.14
ero
-0.14
ropoda
-0.14
ucht
-0.14
eger
-0.14
POSITIVE LOGITS
anske
0.16
лав
0.16
еÑģÑĤва
0.16
cope
0.15
411
0.15
744
0.15
ogle
0.15
Johnson
0.15
sei
0.15
amedi
0.15
Activations Density 0.004%