INDEX
Explanations
references to people involved in legal issues or controversies
New Auto-Interp
Head Attr Weights
0:0.03
1:0.03
2:0.14
3:0.08
4:0.04
5:0.04
6:0.17
7:0.24
8:0.04
9:0.03
10:0.07
11:0.04
Negative Logits
reproduction
-1.26
EngineDebug
-1.24
arine
-1.22
alike
-1.10
wolves
-1.08
duplication
-1.06
inosaur
-1.06
breeding
-1.04
crossover
-1.04
hindsight
-1.04
POSITIVE LOGITS
ğ
1.65
ć
1.50
irez
1.48
quez
1.31
arez
1.26
ón
1.26
vous
1.26
oglu
1.23
�
1.21
enez
1.21
Activations Density 0.084%