INDEX

Explanations

examples and names

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 either

0.72

 counterpart

0.68

 associate

0.67

Victory

0.66

 click

0.66

 divide

0.65

 performing

0.65

 directing

0.64

 notify

0.64

 sold

0.63

POSITIVE LOGITS

示例

0.91

akkhand

0.87

 Beispiele

0.87

ření

0.86

 Nasıl

0.85

වි

0.85

 গুরুত্বপূর্ণ

0.84

äänt

0.83

 ejemplos

0.83

EXAMPLES

0.82

Activations Density 0.052%

No Known Activations