INDEX

Explanations

the most no many each

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

 from

-1.39

красный

-1.31

 There

-1.20

приклад

-1.16

нах

-1.16

：……

-1.16

 there

-1.14

₂,

-1.13

-->

-1.13

 være

-1.13

POSITIVE LOGITS

 would

1.58

 entire

1.45

 then

1.34

一定是

1.34

 deportivo

1.29

 другое

1.29

1.28

 }^{[

1.27

必定

1.25

 wszyscy

1.24

Activations Density 0.060%