INDEX

Explanations

accept yourself and others

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

 από

1.79

 τους

1.71

 на

1.68

 στην

1.65

 και

1.64

ή

1.63

ו

1.63

 שה

1.58

 или

1.57

및

1.56

POSITIVE LOGITS

ちなみに

1.42

 indah

1.38

 demikian

1.29

 tentunya

1.28

 conservative

1.24

蕲

1.22

middels

1.22

 addictive

1.21

omethyl

1.20

ggi

1.19

Activations Density 0.015%