INDEX
Explanations
mentions of individuals named Mike
New Auto-Interp
Negative Logits
wang
-0.19
ne
-0.18
reich
-0.17
weg
-0.16
igne
-0.16
mente
-0.15
izer
-0.15
avou
-0.15
izers
-0.15
nya
-0.15
POSITIVE LOGITS
latter
0.18
iless
0.16
ster
0.15
laus
0.15
aukee
0.15
rowave
0.14
Huckabee
0.14
WAYS
0.14
Rounds
0.14
SELL
0.14
Activations Density 0.012%