INDEX
Explanations
proper nouns related to a specific name "Herman"
mentions of the name "Herman."
New Auto-Interp
Negative Logits
Thumbnails
-0.83
hedral
-0.80
yrim
-0.76
ertodd
-0.75
ulhu
-0.74
anooga
-0.66
ured
-0.65
isted
-0.65
iful
-0.65
attm
-0.62
POSITIVE LOGITS
n
1.28
thal
1.03
nian
1.02
tz
1.01
ns
0.98
stein
0.98
wald
0.98
mens
0.97
nen
0.95
lein
0.94
Activations Density 0.081%