INDEX
Explanations
instances of technical details or specifications
New Auto-Interp
Negative Logits
12
-0.31
11
-0.29
10
-0.28
13
-0.24
twelve
-0.24
Twelve
-0.23
åįģäºĮ
-0.21
14
-0.20
tenth
-0.20
7
-0.20
POSITIVE LOGITS
21
0.29
22
0.28
23
0.25
20
0.23
24
0.23
25
0.23
äºĮåįģ
0.22
nineteen
0.20
Û²Û±
0.19
twenty
0.19
Activations Density 0.103%