INDEX

Explanations

code and documentation headers

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

 therefore

-1.59

jednoc

-1.46

 even

-1.45

 навіть

-1.41

of

-1.34

EVEN

-1.32

even

-1.31

蠣

-1.30

 حتی

-1.28

 même

-1.27

POSITIVE LOGITS

 similares

1.34

 innych

1.29

Another

1.29

 berkaitan

1.27

For

1.26

 Another

1.24

焼く

1.23

姆

1.22

 другого

1.20

美味しかった

1.19

Activations Density 0.002%