INDEX
Explanations
abbreviations or acronyms often involving political entities
references to legislative bills or proposals
New Auto-Interp
Negative Logits
ovich
-0.72
lessly
-0.67
esan
-0.61
coincide
-0.60
enegger
-0.60
modem
-0.60
owsky
-0.59
yright
-0.58
utilitarian
-0.57
roam
-0.57
POSITIVE LOGITS
Ct
0.84
W
0.78
outher
0.77
RNA
0.76
1600
0.74
DAY
0.73
O
0.73
F
0.73
E
0.72
Ws
0.71
Activations Density 0.036%