INDEX
Explanations
words related to specific types of beer
New Auto-Interp
Negative Logits
pregn
-0.80
Debor
-0.67
pard
-0.66
ATIONAL
-0.62
simultane
-0.62
viol
-0.60
ality
-0.60
perse
-0.60
citiz
-0.59
trave
-0.58
POSITIVE LOGITS
strap
1.17
stra
0.94
roach
0.94
ers
0.93
eries
0.90
tails
0.90
yards
0.88
warm
0.86
tail
0.82
yard
0.81
Activations Density 0.021%