INDEX
Explanations
the name "Blake"
occurrences of the name "Blake."
New Auto-Interp
Negative Logits
egal
-0.79
Demand
-0.77
ocard
-0.77
CHO
-0.72
ktop
-0.72
srfAttach
-0.71
oppable
-0.71
nih
-0.69
Lenin
-0.69
ãĥķãĤ©
-0.69
POSITIVE LOGITS
pedia
0.87
rette
0.83
Blake
0.83
Jenner
0.76
Griffin
0.74
leans
0.74
Isa
0.73
more
0.72
mint
0.72
Blake
0.71
Activations Density 0.021%