INDEX

Explanations

classification labels, statements, or categories

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

رة

1.82

 большого

1.47

va

1.46

re

1.45

elow

1.44

𝒌

1.43

VE

1.40

 полного

1.38

 матрицы

1.37

ve

1.36

POSITIVE LOGITS

)]);

1.58

\%,

1.53

ed

1.44

ा

1.41

ेड

1.40

 newcomer

1.37

))],

1.37

◀

1.36

ôs

1.35

]}$.

1.34

Activations Density 0.000%