INDEX

Explanations

variable assignment or code snippets

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

 trabaja

-1.33

 berbagai

-1.30

 medarbe

-1.22

crocs

-1.17

 groote

-1.14

assorted

-1.14

wif

-1.11

july

-1.11

ruka

-1.10

juicy

-1.08

POSITIVE LOGITS

That

1.40

Despite

1.28

Honestly

1.27

Having

1.24

There

1.23

还不错

1.19

Maybe

1.16

From

1.15

After

1.13

PARATUS

1.12

Activations Density 0.004%