INDEX

Explanations

No Explanations Found

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

 demonstra

0.74

 demostrar

0.72

 دکھ

0.69

demon

0.68

 representar

0.67

ayin

0.67

opos

0.66

੩

0.65

 oneness

0.65

 demost

0.65

POSITIVE LOGITS

 person

0.79

Person

0.72

 फायरिंग

0.68

person

0.67

 single

0.67

 comment

0.65

 Person

0.63

Single

0.63

身为

0.62

注释

0.61

Activations Density 0.137%

No Known Activations