INDEX

Explanations

location tracking and GPS

The main thing this neuron does is find technical references to “location” (e.g. location services, APIs, and coordinate‐related code).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

=[];

-1.19

/}.

-1.16

上がった

-1.09

 pimenta

-1.09

 mestre

-1.08

Få

-1.06

 hoor

-1.05

έρα

-1.04

où

-1.03

POSITIVE LOGITS

Formik

1.14

ֵּ

1.09

 measurements

1.07

følge

1.05

 measurement

1.05

 today

1.04

gación

1.04

 then

1.04

jenost

1.03

 data

1.02

Activations Density 0.008%