INDEX
Explanations
proper names or locations
specific news station identifiers or code names associated with news reports
New Auto-Interp
Negative Logits
pora
-0.77
acca
-0.74
disinfect
-0.67
burner
-0.65
pointers
-0.63
hiber
-0.63
anmar
-0.62
footed
-0.62
aceae
-0.61
sep
-0.61
POSITIVE LOGITS
TV
1.05
GBT
0.98
CTV
0.87
NBC
0.86
IX
0.86
ABC
0.85
Alert
0.83
JR
0.83
FOX
0.82
VT
0.82
Activations Density 0.072%