INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

273,612 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Basically

1.52

 상당히

1.43

 Basically

1.39

 بشكل

1.37

 Interestingly

1.35

 praticamente

1.33

 굉장히

1.32

 basically

1.31

(~

1.30

(!

1.30

POSITIVE LOGITS

 whispers

1.35

 sorrow

1.22

 whispered

1.21

 tales

1.18

 hope

1.14

 dreams

1.12

 solace

1.10

 whisper

1.09

 weary

1.06

 whispering

1.02

Activations Density 2.323%

No Known Activations