INDEX
Explanations
phrases emphasizing exception or exclusion
instances of the phrase "all but."
New Auto-Interp
Negative Logits
edu
-0.74
ixon
-0.68
english
-0.63
amba
-0.61
atha
-0.61
instein
-0.59
ADA
-0.58
Corps
-0.58
obyl
-0.58
Neuroscience
-0.57
POSITIVE LOGITS
tons
0.86
theless
0.75
except
0.73
peripher
0.72
tered
0.71
irrespective
0.66
chery
0.65
UF
0.65
excluding
0.62
fortunately
0.61
Activations Density 0.018%