INDEX

Explanations

android layout, code comments

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

もあった

-1.31

未必

-1.24

质疑

-1.24

羈

-1.23

 THEY

-1.16

 autocollant

-1.16

$?

-1.16

 might

-1.16

You

-1.16

 Использу

-1.15

POSITIVE LOGITS

that

1.38

});*/

1.34

ISIONS

1.30

ESSIONAL

1.30

rógeno

1.27

 "}";

1.27

thirds

1.26

韪

1.26

Nosotros

1.26

our

1.23

Activations Density 0.003%