INDEX

Circuit Sparsity

No connected neurons data available

Explanations

indexing array elements

function argument lists (negative activations)

Auto-Interp Tools

Configuration

Prompts (Dashboard)

16,384 prompts, 256 tokens each

Dataset (Dashboard)

neuronpedia/python-code-simplified

Embeds

IFrame

Link

Negative Logits

_order

-0.08

_for

-0.08

_from

-0.07

_str

-0.07

_he

-0.07

_al

-0.07

_counts

-0.07

_with

-0.07

_mo

-0.07

_sum

-0.07

Positive Logits

timal

0.05

straints

0.05

prese

0.05

stac

0.04

path

0.04

 ValueError

0.04

 path

0.04

 typing

0.04

))

0.04

Activations Density 100.000%