INDEX
Explanations
references to law enforcement and police-related contexts
New Auto-Interp
Negative Logits
étoient
-0.46
ckså
-0.43
olingo
-0.42
avoient
-0.41
phosphoric
-0.40
splitlines
-0.39
BYU
-0.39
Clemson
-0.39
Provo
-0.39
Majefty
-0.38
POSITIVE LOGITS
London
1.19
London
1.08
london
0.96
london
0.94
LONDON
0.92
Londres
0.88
伦敦
0.84
LONDON
0.78
Londres
0.78
لندن
0.77
Activations Density 0.328%