INDEX
Explanations
references to individuals in news articles
New Auto-Interp
Negative Logits
vale
-0.16
Harlem
-0.15
ynch
-0.15
_ops
-0.15
èĥĮ
-0.14
NYC
-0.14
bbc
-0.14
sed
-0.14
summar
-0.13
管çIJĨåijĺ
-0.13
POSITIVE LOGITS
columnist
0.21
Column
0.21
column
0.20
metro
0.20
Column
0.19
column
0.18
Tribune
0.18
columns
0.18
Herald
0.18
COLUMN
0.17
Activations Density 0.146%