INDEX

Explanations

interconnectedness and interaction

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

3.03

𝖙

2.41

rooms

2.25

MSN

2.23

 ITEMS

2.19

2.16

render

2.13

 plough

2.12

clk

2.10

follow

2.10

POSITIVE LOGITS

्राष्ट्रीय

3.08

्राष्ट

2.91

 кушымта

2.89

क्स्ट

2.87

ijske

2.79

𝘯

2.72

eal

2.71

újo

2.68

𝘭

2.67

waitForIdleSync

2.51

Activations Density 0.219%