INDEX

Circuit Sparsity

No connected neurons data available

Explanations

attribute access (`.`) completion (negative activations)

min function call

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

heck

-0.05

is

-0.05

 check

-0.05

.is

-0.04

 Check

-0.04

are

-0.04

has

-0.04

 count

-0.03

place

-0.03

 valid

-0.02

POSITIVE LOGITS

loat

0.05

.in

0.05

sys

0.04

 float

0.04

0.03

.f

0.02

the

0.02

new

0.02

 math

0.02

.m

0.01

Activations Density 96.561%