INDEX

Explanations

I feel like

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

显然

-1.14

 évidemment

-1.13

 ação

-1.04

 环境

-1.03

 organização

-1.02

 Organisationen

-1.02

圆

-1.00

 软件

-0.98

TYPED

-0.97

举报

-0.96

POSITIVE LOGITS

 when

1.14

ouchable

1.08

 cuando

1.06

 být

1.03

 something

1.02

at

1.02

 although

1.00

 når

0.99

 maybe

0.98

諒

0.98

Activations Density 0.025%