INDEX

Circuit Sparsity

No connected neurons data available

Explanations

function, class, or import statements

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

No Comments

Negative Logits

all

-0.05

lse

-0.04

dfs

-0.04

lif

-0.04

_row

-0.04

if

-0.04

 elif

-0.03

If

-0.03

all

-0.03

POSITIVE LOGITS

duct

0.04

 column

0.03

quen

0.03

zero

0.03

zip

0.02

enden

0.02

 number

0.02

 queue

0.02

spe

0.01

Activations Density 5.649%