INDEX
Explanations
workshops
the main thing this neuron does is find meaning of identity through relational, embodied, and spiritual context.
New Auto-Interp
Negative Logits
nick
-0.08
nick
-0.08
Pec
-0.08
Cree
-0.08
seguintes
-0.07
http
-0.07
máximo
-0.07
rumours
-0.07
أكبر
-0.07
ต่าง
-0.07
POSITIVE LOGITS
_than
0.13
niż
0.13
Than
0.12
decât
0.12
than
0.12
than
0.12
-than
0.11
_THAN
0.11
besides
0.10
yiş
0.10
Activations Density 0.250%