INDEX

Explanations

pronouns followed by contractions

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

 travaille

1.10

 actually

1.10

◑

1.08

 publicó

1.06

btw

1.05

 ought

1.04

 amazingly

1.04

mib

1.04

 あり

1.03

 avoid

1.03

POSITIVE LOGITS

ه

1.30

1.12

ようになった

1.08

що

0.96

тися

0.86

 زیرا

0.83

aes

0.82

ଛ

0.82

ाल

0.81

leş

0.81

Activations Density 0.073%