INDEX

Circuit Sparsity

No connected neurons data available

Explanations

regular expression match

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

uristic

-0.04

-0.03

ue

-0.02

se

-0.02

No

-0.01

£

-0.01

()<|

-0.01

is

-0.01

POSITIVE LOGITS

time

0.06

mp

0.05

mple

0.05

(map

0.05

(list

0.04

(range

0.04

(max

0.04

(min

0.04

(G

0.04

(str

0.04

Activations Density 43.109%