INDEX
Explanations
prominent names of individuals mentioned in the text
New Auto-Interp
Negative Logits
iqueta
-0.18
agram
-0.17
isy
-0.17
TestCategory
-0.16
emsp
-0.16
cel
-0.16
evin
-0.16
addle
-0.16
coma
-0.15
iad
-0.15
POSITIVE LOGITS
ortality
0.15
Auth
0.15
ette
0.15
aleb
0.14
outer
0.14
-La
0.14
Arbitrary
0.14
980
0.13
lsa
0.13
sha
0.13
Activations Density 0.087%