INDEX
Explanations
discussions of mental health and trauma-related topics
New Auto-Interp
Negative Logits
aniu
-0.16
Reader
-0.14
idl
-0.14
KERNEL
-0.14
hei
-0.14
icorn
-0.13
åģ¶
-0.13
adero
-0.13
uff
-0.13
oup
-0.13
POSITIVE LOGITS
NPR
0.20
listeners
0.20
joins
0.19
(sound
0.19
-anchor
0.19
WX
0.19
Anchor
0.18
listener
0.18
Anchor
0.18
tonight
0.17
Activations Density 0.041%