INDEX

Explanations

"i" followed by verbs of intent or cognition

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

給我

-1.22

 нашего

-1.17

gräns

-1.15

 meinem

-1.14

we

-1.13

 τού

-1.12

VPB

-1.11

our

-1.11

 verksamhet

-1.09

 aktivitet

-1.09

POSITIVE LOGITS

 your

1.34

 want

1.30

 just

1.29

 चुनें

1.19

 will

1.16

了些

1.16

丨

1.12

 vás

1.10

了不少

1.03

 what

1.01

Activations Density 0.016%