INDEX

Explanations

possessive pronoun followed by noun

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

-1.78

-1.36

</em>

-1.33

-1.27



-1.22

 bearbeitet

-1.21

 erscheinen

-1.20

and

-1.20

 gange

-1.20

 οποία

-1.18

POSITIVE LOGITS

 mimpi

1.77

 obligado

1.55

 casado

1.48

 resultaten

1.48

 potre

1.46

 discut

1.43

owna

1.42

مقدمه

1.42

 waard

1.42

本日の

1.41

Activations Density 0.074%