INDEX
Explanations
references to people or entities named "Green" or variations of that name
New Auto-Interp
Negative Logits
isure
-0.16
æĮ¯ãĤĬ
-0.15
raised
-0.15
dra
-0.14
uren
-0.14
ivr
-0.14
redo
-0.14
umin
-0.14
ambda
-0.14
amedi
-0.14
POSITIVE LOGITS
Gre
0.27
gre
0.27
Gre
0.24
GRE
0.20
gree
0.20
Greene
0.20
gre
0.18
enco
0.18
Gr
0.17
estic
0.17
Activations Density 0.016%