INDEX
Explanations
database-related operations and functions
New Auto-Interp
Head Attr Weights
0:0.07
1:0.06
2:0.06
3:0.08
4:0.05
5:0.10
6:0.16
7:0.02
8:0.07
9:0.09
10:0.09
11:0.09
Negative Logits
accompan
-1.75
behavi
-1.60
��
-1.50
afety
-1.49
pestic
-1.48
ibrary
-1.41
ACP
-1.40
��
-1.39
idelines
-1.34
�
-1.33
POSITIVE LOGITS
teammate
1.33
yo
1.28
Doodle
1.25
coin
1.25
siblings
1.23
Omega
1.21
mate
1.21
Jonah
1.17
ilus
1.16
ocate
1.16
Activations Density 0.001%