INDEX

Explanations

special characters in code or math

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

érica

-1.38

銠

-1.36

"}";

-1.36

 pittores

-1.34

 توضی

-1.30

 stalwart

-1.30

先週

-1.29

uses

-1.29

相変わらず

-1.27

obviously

-1.24

POSITIVE LOGITS

 cuando

1.80

 When

1.73

 other

1.51

 different

1.41

 used

1.38

 helps

1.32

 เมื่อ

1.31

 aimed

1.30

1.28

 various

1.27

Activations Density 0.039%