INDEX
Explanations
mentions of the word "berry" at various activation levels
references to cranberries and their variations in different contexts
New Auto-Interp
Negative Logits
OPER
-0.71
Phelps
-0.70
raint
-0.68
escal
-0.67
plur
-0.65
allas
-0.63
itutional
-0.62
pers
-0.60
UAL
-0.60
urities
-0.60
POSITIVE LOGITS
berry
1.15
berries
1.12
bushes
0.97
fruit
0.93
juice
0.92
bush
0.88
juices
0.81
otine
0.80
issance
0.79
kees
0.77
Activations Density 0.030%