INDEX
Explanations
words related to hunger and appetite
New Auto-Interp
Negative Logits
ampo
-0.17
adia
-0.17
arine
-0.16
atto
-0.15
ogl
-0.14
opers
-0.14
enos
-0.14
cher
-0.14
Overs
-0.13
quo
-0.13
POSITIVE LOGITS
/feed
0.16
onData
0.15
_ZERO
0.15
Souls
0.15
ymes
0.15
lust
0.15
-feed
0.15
ibs
0.14
ayi
0.14
ilst
0.14
Activations Density 0.018%