INDEX

Explanations

mentions of names or citations

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

 with

-1.98

but

-1.57

in

-1.38

for

-1.37

on

-1.35

-1.24

or

-1.16

-1.14

-1.13

 both

-1.13

POSITIVE LOGITS

ATEGORY

1.50

makes

1.44

 coelho

1.36

 enoj

1.35

 attes

1.34

 concerne

1.33

 disser

1.32

isait

1.31

 temb

1.30

 craz

1.29

Activations Density 0.061%