INDEX

Circuit Sparsity

No connected neurons data available

Explanations

'(' or '0' or numbers (negative activations)

method definition with `init`

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

 given

-0.09

zero

-0.08

spe

-0.07

...

-0.05

wo

-0.04

ery

-0.03

 input

-0.03

one

-0.03

not

-0.03

er

-0.03

POSITIVE LOGITS

 {↵

0.05

 {}↵

0.05

 []↵

0.04

 {}↵↵

0.03

are

0.03

 product

0.03

 start

0.02

dfs

0.02

 []↵↵

0.02

 source

0.02

Activations Density 99.658%