INDEX

Explanations

</ followed by code constructs

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

 fotógrafo

-1.32

арт

-1.23

haviours

-1.22

 regardé

-1.21

ของ

-1.21

ไม่

-1.21

luka

-1.21

yeah

-1.20

 estudiante

-1.20

เรา

-1.18

POSITIVE LOGITS

 length

1.29

 there

1.23

1.17

1.11

 size

1.10

 number

1.08

 первом

1.06

始まる

1.04

1.02

 each

1.01

Activations Density 0.009%