INDEX
Explanations
the name "Peter" appearing in various contexts
references to the name "Peter" in various contexts
New Auto-Interp
Negative Logits
req
-0.84
eatures
-0.73
ornia
-0.72
BIP
-0.66
inately
-0.64
ees
-0.63
iencies
-0.61
ences
-0.61
iter
-0.59
earable
-0.59
POSITIVE LOGITS
bilt
1.49
borough
1.26
loo
1.04
Thiel
1.01
Pan
0.94
Parker
0.86
Tosh
0.86
Fram
0.85
Gabriel
0.84
Schiff
0.79
Activations Density 0.020%