INDEX

Explanations

question or statement starts

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

or

-1.45

 this

-1.40

 their

-1.30

 with

-1.25

all

-1.20

any

-1.13

get

-1.12

 those

-1.11

go

-1.09

هاز

-1.06

POSITIVE LOGITS

 protože

1.32

Buna

1.30

 vanqu

1.19

gives

1.18

 forbidding

1.16

 angepasst

1.16

蓊

1.15

Gön

1.15

 erzeugt

1.13

Spolja

1.13

Activations Density 0.000%