INDEX

Explanations

comparisons or technical names

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

flags

-0.07

-mÃªme

-0.06

-webpack

-0.06

èĢĮä¸Ķæĺ¯

-0.06

çĶļèĩ³

-0.06

 outcry

-0.06

iggs

-0.06

ogan

-0.06

.Encoding

-0.06

ilib

-0.06

POSITIVE LOGITS

vs

0.10

 versus

0.09

usi

0.08

ynos

0.08

è·¯ä¸ľ

0.08

æĺ¯ä»Ģä¹ĪæĦıæĢĿ

0.07

_vs

0.07

vs

0.07

ä¸ĬçľĭåĪ°

0.07

æľīåĢĭ

0.07

Activations Density 0.263%