INDEX
Explanations
comparisons or contrasts
New Auto-Interp
Negative Logits
obser
-0.73
illary
-0.70
catentry
-0.69
imeter
-0.67
ftime
-0.67
imeters
-0.64
*/(
-0.63
ulative
-0.62
uters
-0.62
otation
-0.60
POSITIVE LOGITS
ours
0.84
anamo
0.80
Sonny
0.71
yours
0.70
algia
0.68
theirs
0.65
aneers
0.63
those
0.62
Phill
0.62
Palest
0.62
Activations Density 0.060%