INDEX
Explanations
mentions of various media and the surrounding context
New Auto-Interp
Negative Logits
↵↵
-0.15
ê²Į
-0.15
aign
-0.15
anken
-0.14
riad
-0.14
kest
-0.14
oise
-0.14
Ñīим
-0.13
IntArray
-0.13
ëŀį
-0.13
POSITIVE LOGITS
they
0.23
there
0.23
Ù쨥ÙĨ
0.21
thì
0.21
we
0.20
they
0.19
it
0.19
они
0.18
вони
0.18
åīĩ
0.18
Activations Density 0.691%