INDEX

Explanations

enum definitions

The neuron fires on numeric literals (tokens representing numbers, including integers and decimals).

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

industan

-1.26

曷

-1.25

훤

-1.23

 $^{\

-1.20

förm

-1.19

$^{

-1.19

ensuche

-1.18

newblock

-1.16

Ɍ

-1.16

存知

-1.15

POSITIVE LOGITS

 these

1.59

1.52

1.44

しているので

1.34

its

1.30

 kesel

1.29

1.27

 levels

1.23

1.22

Activations Density 0.028%