INDEX

Explanations

questions about existence or state

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

).

-1.52

 เน

-1.38

 SUCH

-1.30

 อย่าง

-1.27

 vuole

-1.23

 ของ

-1.23

mbda

-1.20

řejmě

-1.20

 thre

-1.20

POSITIVE LOGITS

 those

1.59

 when

1.37

 where

1.36

ίζ

1.27

 because

1.24

 whether

1.23

 which

1.20

חים

1.17

because

1.17

Why

1.16

Activations Density 0.277%