INDEX
Explanations
phrases that indicate events, reports, or statements in a formal context
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.23
3:0.17
4:0.10
5:0.05
6:0.03
7:0.06
8:0.05
9:0.10
10:0.08
11:0.04
Negative Logits
custod
-1.49
.""
-1.30
overt
-1.26
Nare
-1.26
[*
-1.23
)."
-1.17
Newsletter
-1.16
ibur
-1.15
mortal
-1.12
coc
-1.11
POSITIVE LOGITS
reused
1.62
malink
1.41
widget
1.40
sd
1.35
upper
1.26
Allows
1.25
json
1.25
Released
1.24
starter
1.24
optional
1.23
Activations Density 0.554%