INDEX

Explanations

expressions of thanks or praise

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

 санкт

-1.55

zwi

-1.46

 петербург

-1.39

 when

-1.34

翆

-1.32

躂

-1.31

 afectados

-1.30

 vivía

-1.28

࿊

-1.28

قتل

-1.27

POSITIVE LOGITS

 there

1.51

1.48

1.40

for

1.38

1.32

↵↵

1.26

1.16

饜

1.14

1.13

 chocolat

1.12

Activations Density 0.026%