INDEX

Explanations

programming language keywords

The neuron fires on numeric literals (tokens representing numbers) in code or 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

and

-2.19

mlink

-1.49

is

-1.30

 apreciar

-1.20

 можешь

-1.20

ponge

-1.19

rosion

-1.16

 analizar

-1.15

ransition

-1.13

させていただきました

-1.12

POSITIVE LOGITS

 those

1.42

 свои

1.29

 richesse

1.28

 vengo

1.26

 maje

1.25

 chọn

1.24

vereignty

1.23

 récente

1.21

 précédente

1.20

 ganze

1.18

Activations Density 0.030%