INDEX

Explanations

The neuron is looking for snippets of source code (e.g. package/import declarations, class/interface keywords, and other programming‐language identifiers).

code imports and definitions

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

 incendie

-1.39

 faſt

-1.37

pantalones

-1.31

क्रिया

-1.30

 chargeur

-1.30

Specifik

-1.28

𝛼

-1.27

 itong

-1.25

 moft

-1.23

 ngayon

-1.23

POSITIVE LOGITS

so

1.34

at

1.32

 продукти

1.28

־ה

1.22

 даже

1.22

on

1.20

 services

1.16

can

1.16

 パソコン

1.15

 basically

1.14

Activations Density 0.024%