INDEX
Explanations
phrases related to reassurance and support
New Auto-Interp
Head Attr Weights
0:0.04
1:0.03
2:0.00
3:0.10
4:0.04
5:0.40
6:0.04
7:0.01
8:0.10
9:0.17
10:0.01
11:0.01
Negative Logits
abases
-2.31
isch
-2.16
guiIcon
-2.14
politic
-2.13
disturbed
-2.08
rice
-2.06
agram
-2.06
crit
-2.06
entimes
-2.06
violated
-2.05
POSITIVE LOGITS
Olive
2.31
Archive
2.26
Finish
2.21
Wrap
2.18
Proof
2.16
docs
2.08
onboard
2.01
PowerShell
2.00
promo
2.00
Enjoy
1.99
Activations Density 0.016%