INDEX

Circuit Sparsity

No connected neurons data available

Explanations

comma followed by space (negative activations)

Python's re.match method call

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

dex

-0.05

ser

-0.04

ses

-0.04

se

-0.03

sed

-0.03

si

-0.03

ke

-0.03

tic

-0.03

sible

-0.02

¹

-0.02

POSITIVE LOGITS

input

0.02

 input

0.01

_input

0.01

he

0.01

(input

0.01

.txt

0.01

structions

0.01

En

0.01

(data

0.01

 given

0.01

Activations Density 80.518%