INDEX

Circuit Sparsity

No connected neurons data available

Explanations

print function calls (negative activations)

`%`, `class`, `ord`, `time`, `functools`

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

 None

-0.03

 default

-0.03

[[

-0.02

 False

-0.02

ault

-0.02

 tuple

-0.02

("

-0.02

 pass

-0.02

[(

-0.02

POSITIVE LOGITS

join

0.05

(min

0.03

(max

0.03

(maze

0.03

(range

0.03

(map

0.03

(route

0.03

(n

0.03

(de

0.03

(op

0.03

Activations Density 96.660%