INDEX

Explanations

circuitry and signals

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tbx

-1.46

ﻻ

-1.20

ὔ

-1.20

すごく

-1.18

*;

-1.16

کارت

-1.16

 beijo

-1.14

 sogar

-1.13

Aplica

-1.13

 diventa

-1.11

POSITIVE LOGITS

as

1.38

uuuu

1.32

 кроссовки

1.30

🤑

1.29

🖕

1.29

uuu

1.26

in

1.26

by

1.21

uuuuu

1.20

or

1.18

Activations Density 0.006%