INDEX

Explanations

programming keywords and identifiers

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

türk

-1.23

 parfü

-1.20

 bekämp

-1.17

especie

-1.17

lauben

-1.16

ichtete

-1.14

bàn

-1.13

𝖐

-1.13

März

-1.12

ाउन

-1.10

POSITIVE LOGITS

 costs

1.27



1.21

ză

1.19

 ホビー

1.19

_;

1.13

the

1.11

%``

1.10

 rates

1.09

 الكهرب

1.08

⫹

1.06

Activations Density 0.004%