INDEX

Explanations

names, dates, and numbers

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

ਫ਼

-1.08

ਗ਼

-1.05

 arriver

-1.02

 recipiente

-1.00

 compteur

-1.00

ਖ਼

-0.98

 şeker

-0.97

 balcón

-0.96

 braços

-0.95

 silueta

-0.94

POSITIVE LOGITS

checkbox

0.96

Через

0.88

 pueden

0.85

といっても

0.85

auc

0.84

 ricerche

0.83

обзор

0.81

ၽ

0.81

krati

0.81

 ushort

0.80

Activations Density 0.140%