INDEX
Explanations
verbs related to removal or reduction
phrases related to removal or depletion
New Auto-Interp
Negative Logits
ammy
-0.74
cius
-0.72
enegger
-0.71
bia
-0.69
iannopoulos
-0.69
interstitial
-0.67
joining
-0.66
ioned
-0.66
disclaimer
-0.65
alian
-0.64
POSITIVE LOGITS
scraps
0.84
havoc
0.82
weeds
0.82
roots
0.73
bushes
0.73
Flavoring
0.73
vines
0.72
bits
0.72
chunks
0.72
fragments
0.71
Activations Density 0.142%