INDEX
Explanations
occurrences of the letter 'r'
New Auto-Interp
Head Attr Weights
0:0.08
1:0.08
2:0.08
3:0.08
4:0.08
5:0.09
6:0.09
7:0.07
8:0.07
9:0.08
10:0.08
11:0.08
Negative Logits
declass
-3.10
FEMA
-3.03
flashbacks
-2.74
seism
-2.69
fixme
-2.68
Guam
-2.64
emer
-2.64
probation
-2.63
flashback
-2.56
archae
-2.54
POSITIVE LOGITS
Hook
3.18
Blood
3.02
Skin
2.92
Motor
2.89
Thumbnail
2.61
blood
2.61
spir
2.54
\">
2.50
Buckley
2.50
vor
2.49
Activations Density 0.000%