INDEX
Explanations
references to media outlets reporting news stories
New Auto-Interp
Negative Logits
announce
-0.07
inker
-0.06
istrator
-0.06
uncomment
-0.06
assin
-0.06
Uncomment
-0.06
neigh
-0.06
voksne
-0.06
<b
-0.06
assis
-0.06
POSITIVE LOGITS
reporting
0.13
reports
0.12
report
0.11
reported
0.11
reporter
0.09
Reporting
0.09
reporters
0.09
.report
0.09
outlet
0.09
reports
0.09
Activations Density 0.017%