INDEX
Explanations
words related to law enforcement officers
references to law enforcement officers
New Auto-Interp
Negative Logits
FORE
-0.89
sbm
-0.79
Downloadha
-0.74
committee
-0.71
avez
-0.67
veyard
-0.65
ItemTracker
-0.65
FINEST
-0.64
xual
-0.64
HCR
-0.64
POSITIVE LOGITS
yrights
1.19
cop
1.15
rodu
0.97
ious
0.96
yright
0.95
ortion
0.81
icker
0.79
yp
0.79
cop
0.77
Cop
0.77
Activations Density 0.005%