INDEX

Explanations

has/have limitations or characteristics

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 something

0.44

something

0.43

 sesuatu

0.41

 alguma

0.40

 Something

0.39

 someth

0.38

 suatu

0.37

 lessened

0.37

 etwas

0.37

 altered

0.37

POSITIVE LOGITS

 göst

0.28

 보인다

0.28

贖

0.28

დება

0.27

맞

0.26

示

0.26

铮

0.26

ადა

0.26

 ટી

0.25

 показали

0.24

Activations Density 0.028%