INDEX
Explanations
expressions of enthusiasm or excitement
New Auto-Interp
Negative Logits
relude
-0.14
Fab
-0.14
Virgin
-0.14
leston
-0.14
roys
-0.14
teenth
-0.13
Virgin
-0.13
ibi
-0.13
irts
-0.13
ypo
-0.13
POSITIVE LOGITS
ea
0.23
ikes
0.22
y
0.18
ay
0.17
'all
0.16
anking
0.16
EA
0.16
anked
0.16
oni
0.16
ESS
0.15
Activations Density 0.020%