INDEX

Explanations

through causality or means

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

 tinha

-1.45

 chastity

-1.40



-1.33

ależ

-1.28

risas

-1.28

сят

-1.27

 gegenwär

-1.26

 سقف

-1.25

 aktiven

-1.23

 penanganan

-1.22

POSITIVE LOGITS

 that

1.76

 soulign

1.74

沨

1.59

 those

1.50

hlte

1.45

 renuncia

1.38

 شهرهای

1.37

蔔

1.36

慤

1.34

Activations Density 0.018%