INDEX
Explanations
geographical locations and their characteristics
New Auto-Interp
Negative Logits
-0.56
(
-0.52
-0.49
-0.48
person
-0.47
et
-0.46
<sup>
-0.46
V
-0.45
de
-0.45
↵↵
-0.45
POSITIVE LOGITS
itſelf
1.08
Monfieur
1.04
myſelf
1.04
Efq
1.00
―――――
0.91
themſelves
0.91
Jefus
0.89
auffi
0.87
poffe
0.87
raiſ
0.85
Activations Density 0.208%