INDEX

Explanations

English translations or common phrases

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

neze

0.46

Inser

0.39

 excès

0.36

比如

0.36

uyeron

0.36

痠

0.36

ᕈ

0.35

esc

0.35

 especiales

0.35

дзе

0.35

POSITIVE LOGITS

Pilot

0.42

CCI

0.39

 Pilot

0.39

Ñ

0.39

 artifact

0.38

 ван

0.38

 घोड़ा

0.38

 kickoff

0.37

 Melting

0.37

 adaptability

0.37

Activations Density 0.008%