INDEX

Explanations

work together

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

百

0.79

噢

0.74

 воздействия

0.71

連接

0.70

哦

0.70

 মানুষকে

0.69

 मनोविज्ञान

0.69

 INNER

0.69

 psychology

0.69

 Mono

0.67

POSITIVE LOGITS

 together

1.88

Together

1.53

together

1.51

 Together

1.51

 gemeinsamen

1.51

 juntos

1.49

 jointly

1.37

 gemeinsam

1.34

 mutual

1.33

 gemeinsame

1.30

Activations Density 0.401%