INDEX

Explanations

parsing sql data

The neuron is triggered by numeric literals (numbers) in the text.

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

Liefer

-1.41

这

-1.40

问我

-1.39

 её

-1.36

這

-1.35

Από

-1.33

who

-1.32

庒

-1.32

umplimiento

-1.27

取材

-1.24

POSITIVE LOGITS

Ꮀ

1.45

 cuáles

1.38

 many

1.35

uaire

1.35

 viejos

1.34

 czarny

1.33

 ayrıca

1.32

 name

1.31

 that

1.31

 уважением

1.29

Activations Density 0.022%