INDEX
Explanations
references to copyright or copyright notices
New Auto-Interp
Negative Logits
queues
-0.71
ieri
-0.69
lycer
-0.68
tongues
-0.67
cknow
-0.67
chains
-0.66
handshake
-0.66
imity
-0.66
drills
-0.64
queue
-0.62
POSITIVE LOGITS
Copyright
1.09
2018
1.05
1999
1.02
2017
1.00
2002
1.00
1997
0.98
2005
0.97
1996
0.97
2015
0.97
1995
0.97
Activations Density 0.005%