INDEX

Explanations

words following "time"

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

菇

-0.94

 MÁS

-0.90

 DELLA

-0.90

 stella

-0.89

 acido

-0.88

 devast

-0.88

yez

-0.87

 OGSÅ

-0.87

 hiked

-0.84

mbing

-0.84

POSITIVE LOGITS

 ones

1.03

なもの

0.90

 THIS

0.90

 quelli

0.89

..

0.87

 المقال

0.87

co

0.84

 Results

0.84

 celui

0.83

𝑡

0.83

Activations Density 0.701%