INDEX

Explanations

mathematical symbols and notation

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

 間取り

-2.81

 вони

-2.69

↵

-2.39

趼

-2.34

-2.23

of

-2.19

 imprescin

-2.16

先は

-2.14

 masculinos

-2.08

并未

-2.05

POSITIVE LOGITS

嚳

2.73

Ⲉ

2.44

 wachs

2.27

 Menschheit

2.25

these

2.19

ſam

2.19

蹿

2.17

PageRoute

2.16

鼉

2.13

though

2.11

Activations Density 0.002%