INDEX

Explanations

multi-language interaction prompts

words or word parts in non-English languages, particularly Romance languages (Spanish, Portuguese, French) and Slavic languages (Russian).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

you

-1.92

 naive

-1.69

 новая

-1.55

 part

-1.55

-1.52

 известно

-1.52

jaguar

-1.47

↵↵

-1.46

</h4>

-1.45

 Erweiter

-1.45

POSITIVE LOGITS

얹

1.62

亊

1.58

喼

1.48

ak

1.47

 Danza

1.43

 ankara

1.42

 放題

1.42

Объем

1.41

Ꮔ

1.39

Александр

1.38

Activations Density 0.004%