INDEX
Explanations
references to dates and numerical data points within the text
New Auto-Interp
Negative Logits
mez
-0.15
forme
-0.14
17
-0.13
ATTER
-0.13
abase
-0.13
rique
-0.13
ingles
-0.13
اÙĦاØŃ
-0.12
BarButton
-0.12
à¹ĩà¸Ķ
-0.12
POSITIVE LOGITS
200
0.49
Û²Û°Û°
0.27
197
0.22
202
0.21
198
0.20
Bush
0.20
196
0.19
bush
0.19
204
0.18
000
0.17
Activations Density 0.080%