INDEX

Explanations

preventing harm and exploitation

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

 nifty

1.02

 tasty

0.97

 funky

0.92

 wacky

0.88

 quirky

0.88

=!

0.87

 handy

0.86

 weird

0.85

 annoying

0.83

giz

0.83

POSITIVE LOGITS

 trauma

1.30

 tragically

1.25

 retra

1.18

 heartbreaking

1.09

 compassion

1.06

 traumas

1.05

 Trauma

1.05

 compassionate

1.04

 harm

1.03

 sadly

1.03

Activations Density 1.814%