INDEX
Explanations
first/third person perspective
The neuron flags occurrences of the second‐person pronoun “you.”
New Auto-Interp
Negative Logits
AT
-0.06
“As
-0.06
spawning
-0.06
****************************************
-0.06
igue
-0.06
fr
-0.06
.span
-0.06
(Is
-0.06
.Priority
-0.06
passes
-0.06
POSITIVE LOGITS
\C
0.07
ابر
0.06
كرد
0.06
.security
0.06
نمود
0.06
bourne
0.06
sunscreen
0.06
DRIVER
0.06
으
0.06
so
0.06
Activations Density 0.016%