INDEX

Explanations

German proper nouns and technical terms

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

but

-1.53

〚

-1.38

 حتی

-1.31

titch

-1.20

 دارد

-1.20

bestimmung

-1.19

 brukar

-1.16



-1.16

thical

-1.16

AKS

-1.16

POSITIVE LOGITS

 which

1.85

any

1.54

 then

1.42

 ambayo

1.35

now

1.34

 with

1.29

 later

1.20

 który

1.18

 from

1.18

of

1.18

Activations Density 0.009%