INDEX
Explanations
references to government budget cuts and their impacts
New Auto-Interp
Negative Logits
941
-0.15
ftar
-0.14
irsch
-0.14
istrovstvÃŃ
-0.14
639
-0.14
alach
-0.14
ë͏
-0.13
iggins
-0.13
stát
-0.13
369
-0.13
POSITIVE LOGITS
cuts
0.68
cut
0.59
cuts
0.51
Cut
0.51
CUT
0.49
cut
0.47
-cut
0.47
Cut
0.47
_cut
0.43
cutting
0.42
Activations Density 0.217%