INDEX

Explanations

words starting with un

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

ت

1.76

𝐠

1.48

it

1.41

ლ

1.38

 fluidized

1.38

ו

1.38

dashed

1.37

deadline

1.36

 acyl

1.31

hawk

1.30

POSITIVE LOGITS

 empêcher

1.53

ieke

1.36

gebung

1.33

இ

1.21

icus

1.20

 hề

1.19

ඒ

1.18

Примечания

1.15

 víct

1.15

ষ্ঠ

1.13

Activations Density 0.020%