INDEX

Explanations

conjunctions and sentence endings

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

1.33

0.94

0.93

ా

0.90

dır

0.86

eta

0.84

ed

0.84

...

0.83

POSITIVE LOGITS

そして

1.48

 কিংবা

1.46

 그리고

1.45

あるいは

1.36

または

1.34

 ovvero

1.31

 illetve

1.25

 protože

1.22

乃至

1.21

 odnosno

1.21

Activations Density 0.010%