INDEX
Explanations
the letter 'r' in various contexts
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.08
3:0.08
4:0.08
5:0.08
6:0.09
7:0.08
8:0.08
9:0.08
10:0.07
11:0.07
Negative Logits
rican
-3.65
imentary
-3.35
rontal
-3.13
=/
-3.09
emale
-3.07
ivan
-3.04
ntil
-3.00
ONY
-2.91
ocrin
-2.88
esp
-2.85
POSITIVE LOGITS
arrow
2.86
thumbnail
2.85
leaf
2.84
TP
2.72
bows
2.59
pods
2.57
Caption
2.56
narrow
2.54
leaf
2.51
pod
2.51
Activations Density 0.000%