INDEX

Explanations

personal interest and curiosity

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

1.09

1.07

is

1.04

and

0.98

0.96

、

0.94

0.90

は

0.90

 tempo

0.87

 objective

0.85

POSITIVE LOGITS

 jakieś

1.46

দ্‌

1.38

 öyle

1.34

 trouva

1.30

 совсем

1.28

 něco

1.26

 jakiś

1.25

そういう

1.25

 hề

1.25

્યાં

1.21

Activations Density 0.030%