INDEX

Circuit Sparsity

No connected neurons data available

Explanations

f in list comprehension (negative activations)

variable access or method call `.get()`

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

append

-0.07

.append

-0.06

.strip

-0.05

[int

-0.04

.txt

-0.04

 []↵↵

-0.04

 []↵

-0.04

loat

-0.04

lse

-0.03

(int

-0.03

POSITIVE LOGITS

.is

0.05

].

0.05

.num

0.05

.in

0.04

 file

0.03

..

0.03

Di

0.02

.remove

0.02

 assign

0.02

 word

0.02

Activations Density 72.824%