INDEX

Circuit Sparsity

No connected neurons data available

Explanations

assignment operator (negative activations)

the plus operator or exponentiation

Auto-Interp Tools

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Negative Logits

append

-0.07

.strip

-0.05

.add

-0.05

ush

-0.05

 heapq

-0.04

.split

-0.03

 path

-0.03

add

-0.03

add

-0.03

_path

-0.03

Positive Logits

 {}↵↵

0.04

 initial

0.03

 {}↵

0.03

vai

0.03

 []↵↵

0.03

.n

0.03

 rows

0.02

dfs

0.02

(len

0.02

Activations Density 99.997%