INDEX
Explanations
numerical references and significant dates related to historical events
New Auto-Interp
Negative Logits
usz
-0.15
071
-0.15
rot
-0.15
aga
-0.14
Cly
-0.14
yt
-0.14
leur
-0.14
ffi
-0.13
ugi
-0.13
çı
-0.13
POSITIVE LOGITS
SSF
0.18
Dön
0.15
Him
0.15
Doll
0.15
SS
0.15
olian
0.15
OMIC
0.14
itler
0.14
upo
0.14
GDK
0.14
Activations Density 0.021%