INDEX

Explanations

locations and descriptions

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

 presque

-1.40

其他的

-1.29

Примі

-1.28

 wspania

-1.24

 incarcer

-1.22

ことがあります

-1.22

 abol

-1.22

 cortos

-1.20

 erns

-1.20

 diverses

-1.18

POSITIVE LOGITS

not

1.41

 cuando

1.41

 when

1.40

if

1.25

WithMany

1.23

ске

1.20

 quando

1.17

 когда

1.16

 cazul

1.13

 acompañar

1.12

Activations Density 0.084%