INDEX
Explanations
elements related to academic courses or education
New Auto-Interp
Negative Logits
ÑĦÑĥнда
-0.21
alie
-0.17
$MESS
-0.15
oldur
-0.15
Ľi
-0.15
uru
-0.15
åĩĿ
-0.15
olet
-0.14
amburger
-0.14
orthodox
-0.14
POSITIVE LOGITS
Lenin
0.25
Party
0.20
Len
0.19
Len
0.19
len
0.19
Stalin
0.18
GPU
0.18
party
0.18
len
0.17
Central
0.17
Activations Density 0.063%