INDEX
Explanations
proper names, specifically the name "Alfred."
the name "Alfred" and its frequent occurrences in various contexts
New Auto-Interp
Negative Logits
stakes
-0.83
manship
-0.78
cript
-0.78
uality
-0.73
BOOK
-0.71
MQ
-0.70
OPLE
-0.70
bucks
-0.66
pter
-0.65
hof
-0.65
POSITIVE LOGITS
sson
0.98
icate
0.83
onso
0.81
ulla
0.77
ication
0.74
uria
0.74
acquaintance
0.73
ury
0.73
Penny
0.72
destro
0.72
Activations Density 0.022%