INDEX
Explanations
links to images on Twitter
multiple occurrences of the period punctuation mark
New Auto-Interp
Negative Logits
volunt
-0.69
disadvant
-0.67
conflic
-0.66
civilisation
-0.65
oun
-0.65
challeng
-0.63
Dane
-0.63
conclud
-0.62
nomine
-0.62
surprises
-0.62
POSITIVE LOGITS
1.86
1.08
twitch
1.08
1.05
imgur
1.02
0.96
youtube
0.96
wordpress
0.95
redd
0.93
php
0.93
Activations Density 0.015%