INDEX

Explanations

scaling and normalization

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

orak

0.46

 مجلس

0.42

 avoidable

0.40

όμε

0.39

qry

0.39

 Judicial

0.38

कोर्ट

0.37

fle

0.36

 судеб

0.36

 спи

0.35

POSITIVE LOGITS

 normalization

1.87

 normalizing

1.76

 normalize

1.72

 Normalize

1.63

normalize

1.62

 normalized

1.59

Normalization

1.57

Normalize

1.55

normalization

1.49

 Normalized

1.44

Activations Density 0.177%