INDEX

Explanations

"I" followed by "did" or "do"

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

of

-1.81

to

-1.63

-1.57

-1.39

-1.27

The

-1.21

Their

-1.21

-1.14

tõ

-1.13

Again

-1.12

POSITIVE LOGITS

抡

1.56

!]

1.37

 ciertos

1.33

 pregă

1.33

}>{

1.29

,]

1.27

过来了

1.25

 cierta

1.24

 verkoop

1.24

ített

1.22

Activations Density 0.032%