INDEX
Explanations
references to the political figure Paul Ryan
New Auto-Interp
Negative Logits
oslav
-0.78
Atlantis
-0.74
tainment
-0.70
Notting
-0.68
âĶĢâĶĢ
-0.67
rees
-0.65
hypers
-0.64
raints
-0.63
Jehovah
-0.63
apartheid
-0.63
POSITIVE LOGITS
gren
0.81
air
0.78
omics
0.77
Zin
0.77
cloth
0.76
sels
0.76
icum
0.75
airs
0.75
pler
0.74
Budget
0.69
Activations Density 0.007%