INDEX

Explanations

initial or first steps

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

atable

1.43

还能

1.31

 else

1.31

 nữa

1.25

maintained

1.25

 lagi

1.24

还会

1.23

 anymore

1.23

 كذلك

1.21

他にも

1.20

POSITIVE LOGITS

 beginnings

3.63

 outset

3.60

 inital

3.57

 initial

3.57

Initial

3.57

initial

3.51

first

3.50

 first

3.49

 ersten

3.45

 eerste

3.44

Activations Density 1.026%