INDEX

Circuit Sparsity

No connected neurons data available

Explanations

server.serve_forever()

string formatting (%) or assignment (=) (negative activations)

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

ong

-0.04

lot

-0.03

 oper

-0.03

[-

-0.03

out

-0.03

cy

-0.03

 visited

-0.02

(graph

-0.02

rent

-0.02

POSITIVE LOGITS

raph

0.10

riority

0.09

(op

0.09

hortest

0.09

lable

0.08

cores

0.08

vailable

0.08

ransition

0.08

instance

0.08

[str

0.08

Activations Density 100.000%