INDEX
Explanations
monetary values and numerical data in the text
New Auto-Interp
Negative Logits
eighth
-0.17
акÑģим
-0.17
Eighth
-0.17
ninth
-0.16
Sutton
-0.16
ighth
-0.15
.hxx
-0.14
seventh
-0.14
Ninth
-0.14
ĭ
-0.14
POSITIVE LOGITS
180
0.35
190
0.35
19
0.34
191
0.33
204
0.32
185
0.32
206
0.32
183
0.32
20
0.32
182
0.30
Activations Density 0.080%