INDEX
Explanations
phrases related to upbringing and locations
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.09
3:0.09
4:0.03
5:0.04
6:0.05
7:0.16
8:0.05
9:0.22
10:0.05
11:0.12
Negative Logits
neys
-1.22
rera
-1.21
rip
-1.19
ica
-1.19
effects
-1.14
availability
-1.13
ms
-1.13
enes
-1.12
ads
-1.11
emo
-1.10
POSITIVE LOGITS
Ascension
1.21
Templar
1.20
royalty
1.18
disbel
1.18
srfAttach
1.17
enture
1.16
Reloaded
1.14
independ
1.13
someday
1.13
TAM
1.11
Activations Density 0.011%