INDEX

Explanations

special character delimiters

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

-1.36

 when

-1.33

 despite

-1.25

if

-1.22

 which

-1.17

！』

-1.16

as

-1.16

<bos>

-1.14

 without

-1.14

but

-1.13

POSITIVE LOGITS

 énorm

1.18

 römischen

1.16

 handeln

1.13

為に

1.11

 понятия

1.10

₱

1.09



1.08

事も

1.07

خود

1.05

 ausged

1.05

Activations Density 0.001%