INDEX
Explanations
mentions of the name "Baker" in the text
mentions of the name "Baker."
New Auto-Interp
Negative Logits
Canaver
-0.79
rise
-0.72
meric
-0.65
arching
-0.63
Nazi
-0.63
perse
-0.62
hibition
-0.61
ERAL
-0.60
acting
-0.60
Neph
-0.60
POSITIVE LOGITS
loo
1.37
Baker
0.85
lain
0.84
stown
0.79
VPN
0.78
ieri
0.77
keley
0.74
jee
0.74
eki
0.69
iffs
0.68
Activations Density 0.032%