INDEX
Explanations
occurrences of the word "of"
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.07
3:0.07
4:0.10
5:0.08
6:0.08
7:0.08
8:0.08
9:0.09
10:0.08
11:0.08
Negative Logits
upfront
-2.48
slam
-2.38
conn
-2.37
wholesale
-2.37
rel
-2.25
actory
-2.24
Leeds
-2.24
avid
-2.22
letter
-2.21
brand
-2.21
POSITIVE LOGITS
___
2.85
":{"2.78
RPG
2.62
Stats
2.58
OPS
2.56
Joshua
2.55
NASA
2.44
thood
2.41
Sanders
2.40
CAP
2.38
Activations Density 0.000%