INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.09
1:0.04
2:0.09
3:0.09
4:0.09
5:0.07
6:0.08
7:0.08
8:0.10
9:0.07
10:0.07
11:0.07
Negative Logits
dated
-1.79
stocks
-1.70
isable
-1.61
utral
-1.58
lished
-1.58
uted
-1.58
intage
-1.58
clusive
-1.55
stals
-1.54
linked
-1.53
POSITIVE LOGITS
reader
1.71
ín
1.54
walks
1.43
winds
1.43
discovering
1.39
emo
1.35
IO
1.35
sne
1.34
obos
1.33
crowds
1.32
Activations Density 0.000%
No Known Activations
This feature has no known activations.