INDEX

Circuit Sparsity

No connected neurons data available

Explanations

list items separated by commas (negative activations)

recursive binary tree insertion

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

_grid

-0.02

 assign

-0.01

 process

-0.01

structions

-0.01

 grid

-0.01

assign

-0.01

->

-0.01

adj

-0.01

 sele

-0.01

POSITIVE LOGITS

(point

0.03

(state

0.03

(file

0.03

(filename

0.03

(line

0.03

(node

0.03

(a

0.02

(current

0.02

(path

0.02

(e

0.02

Activations Density 87.754%