INDEX

Explanations

unlocks and acquisition

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

 brevi

-1.17

 oogen

-1.11

 censi

-1.11

ੴ

-1.10

 maten

-1.08

 traged

-1.08

 tempel

-1.08

 bandung

-1.07

 beda

-1.05

 satte

-1.05

POSITIVE LOGITS

 after

1.56

 from

1.55

to

1.29

 first

1.23

 later

1.20

by

1.19

you

1.19

for

1.16

 obtain

1.14

 only

1.11

Activations Density 0.023%