INDEX

Circuit Sparsity

No connected neurons data available

Explanations

' not in' keyword or `not` for conditions

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

-0.03

ft

-0.03

_to

-0.03

ig

-0.03

np

-0.02

anage

-0.02

ir

-0.02

olver

-0.02

.st

-0.02

POSITIVE LOGITS

all

0.04

ase

0.03

ame

0.03

 initial

0.02

ameters

0.02

ate

0.02

dition

0.02

un

0.02

uild

0.02

ates

0.02

Activations Density 69.767%