INDEX

Explanations

project configuration and package include

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

ższy

-0.85

Kla

-0.85

 посо

-0.82

manns

-0.81

肥

-0.80

 toek

-0.79

lits

-0.79

捨て

-0.79

 Kirs

-0.79

 tind

-0.78

POSITIVE LOGITS

 Condition

0.90

 dianggap

0.88

 include

0.85

自分

0.80

Include

0.79

ἴ

0.79

 Physical

0.78

Physical

0.77

 Include

0.76

roskop

0.76

Activations Density 0.053%