INDEX
Explanations
specific names and identifiers related to people and their affiliations
New Auto-Interp
Negative Logits
d
-0.14
rada
-0.13
zz
-0.13
Sund
-0.13
Jad
-0.13
CHAN
-0.13
brainstorm
-0.13
²
-0.13
ese
-0.13
amil
-0.12
POSITIVE LOGITS
_k
0.27
K
0.24
$k
0.24
ÂłK
0.24
Ðļ
0.23
ignKey
0.23
_K
0.23
K
0.23
Âłk
0.22
*k
0.21
Activations Density 0.494%