INDEX

Circuit Sparsity

No connected neurons data available

Explanations

list index followed by attribute access

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

No Comments

Negative Logits

-0.05

in

-0.02

us

-0.02

ip

-0.02

uple

-0.02

==

-0.02

us

-0.02

lat

-0.01

(map

-0.01

[-

-0.01

POSITIVE LOGITS

(path

0.10

 path

0.07

distances

0.05

path

0.05

arest

0.04

jac

0.04

_distances

0.04

.path

0.04

etween

0.04

distan

0.04

Activations Density 84.538%