INDEX

Explanations

possessive pronouns and postpositions

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

さを

0.64

টাই

0.57

ğini

0.55

效果

0.54

мую

0.53

 होते

0.53

Ꮞ

0.52

음을

0.51

자를

0.51

りを

0.51

POSITIVE LOGITS

にとって

1.39

にとっては

1.27

에게

1.09

 számára

1.02

 විසින්

1.01

에서는

0.97

における

0.97

 jaoks

0.95

 কর্তৃক

0.93

 પાસે

0.91

Activations Density 0.037%