INDEX

Circuit Sparsity

No connected neurons data available

Explanations

else: (negative activations)

list initialization

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

.position

-0.06

_coords

-0.03

_position

-0.03

 positions

-0.03

.split

-0.03

.de

-0.03

_loc

-0.03

 coordinates

-0.03

 column

-0.03

index

-0.02

POSITIVE LOGITS

 Create

0.07

itial

0.06

stance

0.05

 Initialize

0.05

 defaultdict

0.04

.graph

0.04

[[

0.04

network

0.04

etween

0.04

_graph

0.03

Activations Density 96.885%