INDEX

Explanations

numerical comparisons

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

 brune

-1.55

壅

-1.51

时间

-1.50

«.

-1.49

Ò

-1.40

 каже

-1.39

wartet

-1.37

mathrm

-1.37

 soos

-1.35

and

-1.34

POSITIVE LOGITS

 other

1.98

都不是

1.64

 ningún

1.59

都需要

1.59

都是在

1.52

 others

1.50

 caiu

1.45

ቍ

1.43

都已经

1.42

 ocorreu

1.38

Activations Density 0.015%