INDEX

Explanations

affirmations and factual statements

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

 fere

0.72

 किसी

0.64

 terk

0.63

(\

0.62

direito

0.61

NIH

0.60

uttam

0.60

എ

0.59

 ആയി

0.59

Hoff

0.59

POSITIVE LOGITS

確かに

1.60

 실제로

1.47

 действительно

1.40

 indeed

1.27

 কথাটা

1.23

 effectivement

1.21

 Indeed

1.18

Indeed

1.16

 doğrud

1.13

确实

1.12

Activations Density 0.095%