INDEX

Explanations

specific entities and their contexts

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

has

-1.38

 sebelumnya

-1.35

 jego

-1.34

 является

-1.27

is

-1.25

另一方面

-1.22

 его

-1.20

個人的には

-1.20

ado

-1.18

POSITIVE LOGITS

 when

1.91

 Dennoch

1.66

but

1.55

𝕿

1.52

тувати

1.51

tahanan

1.47

 Trotzdem

1.47

 this

1.47

 responsáveis

1.40

when

1.37

Activations Density 0.164%