INDEX
Explanations
words related to physical braces and supports
references to braces and bracelets
New Auto-Interp
Negative Logits
DEM
-0.79
Kin
-0.70
---------------
-0.70
Population
-0.69
Agent
-0.68
ULT
-0.66
Lenin
-0.65
Water
-0.65
agents
-0.64
Hunt
-0.64
POSITIVE LOGITS
brace
1.53
braces
1.48
lets
1.09
ifix
0.96
brackets
0.94
bracelet
0.92
straps
0.89
brace
0.86
itude
0.83
wcs
0.82
Activations Density 0.006%