INDEX

Explanations

code documentation comments

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

in

-1.48

providedIn

-1.44

 mutta

-1.41

 from

-1.37

new

-1.33

 more

-1.29

 bringing

-1.27

 with

-1.25

häuse

-1.24

 eight

-1.19

POSITIVE LOGITS

1.91

1.45

unn

1.29

 shimmering

1.27

 wondrous

1.25

 quintessential

1.23

 kleinere

1.23

iiii

1.20

(>

1.20

 focuses

1.20

Activations Density 0.009%