INDEX
Explanations
expressions of personal sentiments and reflections
New Auto-Interp
Negative Logits
derp
-0.15
elman
-0.15
dyst
-0.14
abinet
-0.14
iesel
-0.14
Offline
-0.14
statuses
-0.14
Binder
-0.14
elong
-0.14
catchy
-0.13
POSITIVE LOGITS
fuck
0.16
sez
0.15
-thumb
0.15
_thumb
0.15
fucked
0.15
Concept
0.15
Mailer
0.15
kaz
0.15
gov
0.15
åĥķ
0.15
Activations Density 0.225%