INDEX
Explanations
phrases related to change and transition over time
New Auto-Interp
Negative Logits
Sadd
-0.14
ắc
-0.14
/Library
-0.14
زÙĨ
-0.14
ëĮĢë¡ľ
-0.14
zM
-0.14
asti
-0.13
Richie
-0.13
ä½µ
-0.13
è͵
-0.13
POSITIVE LOGITS
subs
0.57
subs
0.43
ab
0.40
dissip
0.32
rec
0.28
peter
0.27
sub
0.27
_subs
0.27
tapered
0.26
taper
0.26
Activations Density 0.178%