INDEX
Explanations
occurrences of the word "live."
New Auto-Interp
Head Attr Weights
0:0.05
1:0.04
2:0.09
3:0.09
4:0.09
5:0.06
6:0.07
7:0.12
8:0.09
9:0.06
10:0.07
11:0.09
Negative Logits
shenan
-1.85
���
-1.77
Reloaded
-1.73
explan
-1.73
decoding
-1.67
mathemat
-1.61
unbeliev
-1.57
reluct
-1.56
arrang
-1.56
rul
-1.55
POSITIVE LOGITS
imentary
2.02
nces
1.99
uid
1.92
spot
1.89
apons
1.82
locks
1.82
borough
1.80
houses
1.79
tip
1.77
nai
1.77
Activations Density 0.000%