INDEX

Explanations

duration and time periods

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 dilig

-0.10

 Roth

-0.09

oser

-0.09

arget

-0.09

 Invasion

-0.09

eki

-0.09

lei

-0.09

ago

-0.09

OCR

-0.09

avi

-0.09

POSITIVE LOGITS

 seconds

0.12

 until

0.12

 lasts

0.12

 till

0.11

 lasted

0.11

until

0.11

 lasting

0.10

si

0.10

seconds

0.10

 longer

0.10

Activations Density 0.045%

No Known Activations