INDEX

Explanations

units and specifications

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

 бампер

-1.42

髂

-1.35

PhysRevLett

-1.34

 туры

-1.26

 commence

-1.25

骶

-1.24

emplares

-1.23

 сковоро

-1.22

🗺

-1.20

 futbolista

-1.18

POSITIVE LOGITS

，

1.57

：

1.42

 different

1.34

；

1.30

、

1.24

 with

1.23

 può

1.21

ﷻ

1.21

𓏸

1.20

 others

1.19

Activations Density 0.026%