INDEX

Explanations

past tense action verbs

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



-1.84

of

-1.64

amerikan

-1.50

we

-1.33

 približ

-1.32

 których

-1.30

\}$,

-1.30



-1.27

masalah

-1.27

Jäh

-1.26

POSITIVE LOGITS

2.09

1.64

’

1.46

 reprez

1.41

the

1.34

 пришли

1.34

</strong>

1.32

1.23

しかも

1.23

 utilisées

1.22

Activations Density 0.161%