INDEX

Explanations

apparent or implied

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

的名字

-0.66

angal

-0.66

رد

-0.66

 flüs

-0.66

 biển

-0.64

enei

-0.64

 unexplored

-0.63

訟

-0.63

teni

-0.62

 Ansel

-0.61

POSITIVE LOGITS

 apparent

5.97

apparent

4.94

 Apparent

4.75

 aparente

4.13

 apparente

3.75

 apparently

3.16

apparently

2.78

 seeming

2.67

 Apparently

2.64

Apparently

2.59

Activations Density 0.119%