INDEX

Explanations

microscopic and molecular details

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

irik

-0.08

curr

-0.08

ç»¼åĲĪå¾ģ

-0.07

apun

-0.07

ativamente

-0.07

OTH

-0.07

äºĭä¸ļä¸Ĭ

-0.07

orias

-0.07

á»«a

-0.07

wali

-0.07

POSITIVE LOGITS

 underlying

0.13

 microscopic

0.11

å¾®è§Ĥ

0.11

å±ĤéĿ¢

0.10

å±ĤéĿ¢çļĦ

0.09

 underneath

0.09

 molecular

0.09

olecular

0.09

atomic

0.08

Atomic

0.08

Activations Density 0.049%

No Known Activations