INDEX
Explanations
details about specific individuals, institutions, or locations related to organizations and their connections
New Auto-Interp
Negative Logits
rrggbb
-0.93
<unused52>
-0.87
<unused68>
-0.87
<unused14>
-0.87
<unused16>
-0.87
<unused21>
-0.86
<unused79>
-0.86
[@BOS@]
-0.86
<unused74>
-0.86
<unused8>
-0.86
POSITIVE LOGITS
unspecified
0.43
Unspecified
0.43
&
0.43
,
0.42
-
0.39
|
0.39
&&
0.38
.
0.38
/
0.38
UNKNOWN
0.38
Activations Density 0.682%