INDEX
Explanations
Code documentation
The neuron activates on structural markup tokens—i.e. the bracketed labels and tag delimiters (like “[”, “/”, and tag names) that mark sections of the text.
New Auto-Interp
Negative Logits
"=",
-0.06
CONSTANT
-0.06
ーテ
-0.06
Fans
-0.06
운
-0.06
�인
-0.06
ือถ
-0.06
Tire
-0.06
assum
-0.06
通
-0.05
POSITIVE LOGITS
Ashley
0.07
PS
0.07
Programmer
0.06
Banana
0.06
PixelFormat
0.06
murderer
0.06
enz
0.06
education
0.06
prisoner
0.06
-highlight
0.06
Activations Density 0.007%