INDEX
Explanations
words related to specific places or people, particularly focusing on names with 'imb' and 'rob' in them
proper nouns, particularly names and organizations
New Auto-Interp
Negative Logits
åħī
-0.74
creen
-0.72
gage
-0.71
ãĥī
-0.68
=#
-0.66
ORIG
-0.65
sburg
-0.65
Ú
-0.64
geist
-0.64
Painter
-0.64
POSITIVE LOGITS
odies
1.21
iotics
1.12
untu
1.05
ilib
1.05
odied
1.04
ruary
1.01
earance
0.98
razil
0.98
ead
0.97
acterial
0.94
Activations Density 0.038%