INDEX
Explanations
themes related to personal experiences and family influences
New Auto-Interp
Negative Logits
uche
-0.15
remen
-0.14
.kotlin
-0.14
Bryant
-0.13
ingles
-0.13
_
-0.13
↵
-0.13
Husband
-0.13
830
-0.13
ik
-0.12
POSITIVE LOGITS
growing
1.05
Growing
0.94
Growing
0.88
grew
0.83
-growing
0.80
grows
0.75
grow
0.70
grow
0.63
Grow
0.61
-grow
0.59
Activations Density 0.404%