INDEX

Explanations

temperature parameter in LLMs

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ğından

1.23

ㅑ

1.13

ğın

1.05

𝗕

1.04

ড়াল

1.04

λλη

1.01

𝗨

1.01

થમ

1.01

 wesentlich

1.00

foaf

0.98

POSITIVE LOGITS

 That

1.73

 Although

1.56

 There

1.54

 When

1.53

 This

1.53

If

1.52

 that

1.52

And

1.51

and

1.49

is

1.48

Activations Density 0.029%