INDEX

Circuit Sparsity

No connected neurons data available

Explanations

opening parenthesis of a function call

list index and slice (negative activations)

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

out

-0.06

tic

-0.05

has

-0.03

is

-0.03

ariable

-0.03

it

-0.02

ny

-0.02

two

-0.02

own

-0.02

all

-0.02

POSITIVE LOGITS

 Returns

0.06

un

0.06

pi

0.05

0.04

 Output

0.04

 Return

0.03

are

0.03

qu

0.03

÷

0.03

Á

0.03

Activations Density 99.996%