INDEX

Explanations

model I cannot/understand

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

 Rooms

0.69

ibol

0.68

වින්

0.67

Ph

0.67

ඉ

0.66

 FIELD

0.66

ើ

0.65

 Field

0.65

getRedTeam

0.64

 Instrument

0.64

POSITIVE LOGITS

 legal

0.59

 springs

0.54

 २४

0.53

 quadruple

0.53

转换为

0.52

۴

0.52

fed

0.52

 LGBTQ

0.51

۴

0.51

 feed

0.50

Activations Density 0.150%