INDEX

Explanations

these followed by nouns

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

☆☆☆☆☆

-1.23

jų

-1.23

 where

-1.16

ógico

-1.13

 Chỉ

-1.12

Часть

-1.11

$};

-1.10

тых

-1.09

 Pilate

-1.09

𝗼

-1.09

POSITIVE LOGITS

are

1.45

時も

1.38

思った

1.38

 وه

1.24

 beiden

1.23

美味しそう

1.17

above

1.15

змом

1.15

うれ

1.13

倆

1.13

Activations Density 0.075%