INDEX

Explanations

various topics and categories

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

 plafon

-1.26

 gebre

-1.12

 poë

-1.11

 grij

-1.10

の部分

-1.09

 groet

-1.09

 modellen

-1.05

 organes

-1.05

 verander

-1.04

 mencionados

-1.04

POSITIVE LOGITS

for

1.38

 reviews

1.24

pdf

1.20

on

1.16

is

1.16

 with

1.14

in

1.12

 without

1.10

no

1.04

to

1.00

Activations Density 0.019%