INDEX

Explanations

legal case citations

This neuron fires on programming language keywords—especially “export,” “import,” and “type”—and also numeric literals in code.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 this

-2.03

 your

-1.72

 acoged

-1.54

 nejen

-1.48

 sanitarias

-1.38

 eléctricas

-1.32

his

-1.30

 ganzes

-1.27

 verksam

-1.24

its

-1.23

POSITIVE LOGITS

chable

1.45

of

1.39

})$.

1.38

krishnan

1.36

仍

1.33

ﻢ

1.30

 חיצוניים

1.27

ซึ่ง

1.27

హ

1.27

 alertDialog

1.24

Activations Density 0.073%