INDEX

Explanations

sorry / forgive

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

èĢĮä¸Ķ

-0.07

 totally

-0.06

 wording

-0.06

OCK

-0.06

åĬ¨èĦĳ

-0.06

å¹¶ä¸Ķ

-0.06

 tasty

-0.06

æľīåħ³åįķä½į

-0.06

 annoying

-0.06

å¥½å¤ļ

-0.06

POSITIVE LOGITS

æĬĺä¸įæī£

0.08

↵   ↵

0.07

æīĵéĢłæĪĲä¸º

0.07

 methodologies

0.07

ague

0.07

 Ð¿ÐµÑĢÐµÐ³Ð¾

0.07

ëħĢ

0.07

 pomme

0.07

è¯·åĲĦä½į

0.07

 NotImplemented

0.07

Activations Density 0.005%