INDEX

Explanations

bold markers after Chinese punctuation

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

tive

4.20

3.70

tions

3.43

ture

3.35



3.01

tio

2.98

tion

2.92

mero

2.89

genus

2.79

р

2.78

POSITIVE LOGITS

痪

2.89

ीय

2.74

iques

2.60

 ticked

2.55

er

2.49

ᴇ

2.48

 ilmiah

2.47

ки

2.45

︎

2.41

संपादन

2.41

Activations Density 0.000%