INDEX

Explanations

comparative words followed by than

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

その他

0.73

 খুব

0.70

 cukup

0.69

 abbastanza

0.69

 suffisamment

0.69

 достат

0.68

 đủ

0.68

 Weitere

0.67

 Beste

0.66

 güzel

0.66

POSITIVE LOGITS

 than

5.28

than

4.17

 Than

4.12

Than

3.85

 niż

3.68

än

3.26

 kuin

3.13

 decât

3.13

 THAN

2.74

 než

2.61

Activations Density 1.166%