INDEX

Explanations

hard conversations, work, or time

hard work

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ಬು

0.42

ईद

0.41

 ভয়াবহ

0.41

 أهم

0.41

ಜ್ಯ

0.40

মন্ত

0.39

翩

0.38

nta

0.38

itesi

0.38

重要な

0.38

POSITIVE LOGITS

wired

1.03

earned

0.87

boiled

0.86

fought

0.86

hitting

0.84

nosed

0.83

coded

0.82

pressed

0.78

core

0.76

scr

0.73

Activations Density 0.085%