INDEX
Explanations
instances of quoted speech in the text
New Auto-Interp
Negative Logits
addock
-0.15
iani
-0.15
rast
-0.14
avad
-0.14
iegel
-0.14
ashtra
-0.13
ublik
-0.13
.Apis
-0.13
stead
-0.13
iever
-0.13
POSITIVE LOGITS
ÄĽtÃŃ
0.17
rij
0.15
dre
0.14
еÑĤÑĮ
0.14
rib
0.14
gee
0.14
trib
0.14
roph
0.14
-*-č↵
0.13
ÑĢоÑģÑĤ
0.13
Activations Density 0.003%