INDEX
Explanations
mentions of specific individuals named "Ma"
the name "Ma" in various contexts
New Auto-Interp
Negative Logits
ij士
-0.79
ses
-0.76
tics
-0.76
starter
-0.75
tyard
-0.75
lined
-0.74
tained
-0.74
suit
-0.71
due
-0.69
irrel
-0.68
POSITIVE LOGITS
estro
1.15
ureen
1.11
Ma
0.95
uth
0.90
emon
0.90
isel
0.89
plin
0.81
iami
0.79
ire
0.79
isan
0.78
Activations Density 0.007%