INDEX
Explanations
words related to a particular name - "Parnell"
instances of the substring "arn" within words
New Auto-Interp
Negative Logits
berman
-0.67
BILITY
-0.66
HER
-0.65
lda
-0.64
ongyang
-0.62
BILITIES
-0.60
Dare
-0.60
plete
-0.58
©¶æ
-0.58
>>>>>>>>
-0.58
POSITIVE LOGITS
ataka
1.29
ivals
1.09
ished
1.02
ival
1.01
emouth
0.98
aby
0.96
sworth
0.93
ell
0.93
ishment
0.91
ais
0.88
Activations Density 0.045%