INDEX
Explanations
references to students and their experiences
New Auto-Interp
Head Attr Weights
0:0.06
1:0.07
2:0.08
3:0.08
4:0.07
5:0.08
6:0.07
7:0.07
8:0.09
9:0.09
10:0.10
11:0.08
Negative Logits
SPONSORED
-1.58
CHR
-1.49
Magikarp
-1.41
weeney
-1.37
natureconservancy
-1.34
ervatives
-1.31
mage
-1.30
Slate
-1.25
FN
-1.25
Dialogue
-1.21
POSITIVE LOGITS
lihood
1.61
haun
1.34
veh
1.30
alle
1.30
gart
1.30
destro
1.28
quit
1.25
estimation
1.22
classification
1.21
acket
1.19
Activations Density 0.000%