INDEX
Explanations
Arabic words or phrases related to legal or official documentation
New Auto-Interp
Negative Logits
CX
-0.18
Newport
-0.17
Essex
-0.16
CT
-0.16
deniz
-0.15
CCP
-0.15
CID
-0.15
Cairo
-0.14
Warwick
-0.14
Gir
-0.14
POSITIVE LOGITS
Minnesota
0.50
Minnesota
0.46
Minneapolis
0.38
MN
0.37
Potato
0.37
MN
0.35
potato
0.31
Fargo
0.31
Barnes
0.30
Mn
0.30
Activations Density 0.001%