INDEX
Explanations
instances where an outcome is described as a result of a preceding action or event
instances of the phrase "as a result."
New Auto-Interp
Negative Logits
undai
-0.76
tradem
-0.72
bolted
-0.68
spaced
-0.68
cot
-0.67
bor
-0.66
millenn
-0.65
notor
-0.64
impe
-0.64
icrobial
-0.63
POSITIVE LOGITS
iments
0.85
ivity
0.83
result
0.81
result
0.79
iveness
0.77
Result
0.76
iment
0.76
ively
0.75
Results
0.73
hess
0.73
Activations Density 0.029%