INDEX

Explanations

position and alignment in text or code

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

ּוֹ

-1.28

ֶּ

-1.27

 проходят

-1.24

 Polskiej

-1.23

 ホビー

-1.16

掲示

-1.15

 дают

-1.15

 sufrir

-1.15

ִּ

-1.13

ruhe

-1.13

POSITIVE LOGITS

 with

1.34

 dampak

1.26

on

1.22

ׇ

1.20

 aturan

1.19

 solusi

1.17

 most

1.16

 pertanian

1.15

торт

1.10

 mundo

1.08

Activations Density 0.007%