INDEX

Explanations

parts of domain names

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

and

-1.40

 while

-1.27

しましたが

-1.11

нале

-1.11

 during

-1.09

Taman

-1.04

capace

-1.01

 amidst

-1.01

 would

-1.00

-0.99

POSITIVE LOGITS

 rayures

1.30

fting

1.18

 fortsatt

1.16

ueira

1.15

。

1.13

/***

1.12

 CAME

1.10

 rencontrer

1.09

 alltid

1.08

mRNA

1.08

Activations Density 0.009%