INDEX

Explanations

names and technical terms

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

 их

-1.50

 their

-1.50

homonymie

-1.38

 with

-1.37

it

-1.36

 this

-1.18

他們的

-1.18

৷

-1.13

 falleció

-1.12

 tört

-1.11

POSITIVE LOGITS

戋

1.25

vs

1.23

'&

1.18

šiu

1.16

 versus

1.16

aaa

1.13

alers

1.11

냑

1.10

ebly

1.10

φα

1.09

Activations Density 0.219%