INDEX

Explanations

numbers and specific entities

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

 Για

-1.30

殽

-1.24

鶫

-1.20

its

-1.16

presumably

-1.13

を開始

-1.12

jours

-1.12

どういう

-1.11

 magnifiques

-1.11

roxene

-1.10

POSITIVE LOGITS

此外

1.27

 nahezu

1.08

メニューは

1.05

 verschiedene

1.05

大学の

1.04

1.02

0.98

 zahlreiche

0.97

 emphasized

0.96

Activations Density 0.028%