INDEX
Explanations
names and surnames
proper nouns, specifically names of people and places
New Auto-Interp
Negative Logits
Plex
-0.77
ADRA
-0.76
PASS
-0.76
FACE
-0.70
overwhelming
-0.69
Vote
-0.67
Issue
-0.66
Tokens
-0.65
FIX
-0.65
actionDate
-0.62
POSITIVE LOGITS
tein
1.06
Jr
1.02
oglu
0.97
Sr
0.93
oulos
0.93
III
0.90
icz
0.87
QC
0.84
zyk
0.84
ensis
0.82
Activations Density 0.325%