INDEX

Explanations

numbers following percentages

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

 about

-1.73

-1.59

两个

-1.55

४

-1.49

.*;

-1.47

one

-1.45

and

-1.40

 tylko

-1.38

หรือ

-1.36

POSITIVE LOGITS

of

2.38

видео

1.49

おわりに

1.36

錚

1.34

のではないでしょうか

1.27

 optimieren

1.25

 klassischen

1.24

где

1.23

同学们

1.22

のかもしれません

1.22

Activations Density 0.026%