INDEX
Explanations
expressions of anticipation and excitement
New Auto-Interp
Negative Logits
ugg
-0.06
did
-0.06
beep
-0.06
Permanent
-0.06
лев
-0.06
eventual
-0.06
ennes
-0.06
irie
-0.06
oods
-0.06
ียà¸ļ
-0.06
POSITIVE LOGITS
excited
0.11
hope
0.10
Hope
0.10
æľŁå¾ħ
0.10
excitement
0.10
hop
0.09
hope
0.09
hoping
0.09
Hope
0.09
exciting
0.09
Activations Density 0.070%