INDEX

Explanations

salutation to name or title

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

 Typing

1.67

的话

1.53

प्रिय

1.52

้

1.48

 Göteborg

1.47

がいる

1.45

સર

1.43

 Laufe

1.41

та

1.39

 Failing

1.38

POSITIVE LOGITS

er

2.09

llä

1.95

1.88

1.85

1.84

owanej

1.77

lly

1.77

 nCenters

1.75

 jambes

1.73

Activations Density 0.005%