INDEX

Explanations

programming imports and functions

This neuron detects programming‐language syntax elements, especially dotted identifiers and semicolons.

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

 such

-1.80

so

-1.46

 anadolu

-1.41

 caminhão

-1.38

 dekoratif

-1.34

 diing

-1.27

decoração

-1.22

猡

-1.21

ּוֹ

-1.20

ְּ

-1.17

POSITIVE LOGITS

 عندما

1.38

Berikut

1.35

ׇ

1.33

ﷲ

1.30

 الجلد

1.27

 بينما

1.23

thay

1.20

的時候

1.19

yelidikan

1.18

isiä

1.16

Activations Density 0.030%