INDEX

Circuit Sparsity

No connected neurons data available

Explanations

list element after number (negative activations)

function call argument or definition

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

visited

-0.05

 visited

-0.05

isited

-0.04

rontier

-0.03

'.

-0.02

dfs

-0.02

queue

-0.02

 stack

-0.02

ycle

-0.02

POSITIVE LOGITS

uples

0.04

uple

0.04

 tuple

0.03

ab

0.02

qrt

0.02

abs

0.02

mbol

0.02

lit

0.01

 Tuple

0.01

 base

0.01

Activations Density 70.008%