INDEX

Explanations

talent shows and competitions

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

↵

-1.47

</tr>

-1.30

and

-1.29

 våra

-1.23

...";

-1.23

we

-1.21

 cervello

-1.21

 algunas

-1.17

因为

-1.16

之际

-1.16

POSITIVE LOGITS

all

1.73

kward

1.51

 vody

1.50

on

1.50

 just

1.34

',

1.33

豆

1.28

®,

1.27

Activations Density 0.026%