INDEX

Explanations

single, small items

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

们

1.50

 segala

1.40

များကို

1.30

 모든

1.27

 সবই

1.27

গুলির

1.25

들을

1.25

 allerlei

1.24

 numerosi

1.23

那些

1.22

POSITIVE LOGITS

 consecutive

1.67

 apiece

1.56

 consecut

1.47

secutive

1.43

 unrelated

1.39

 Consecutive

1.28

 consecutively

1.27

쨰

1.26

 подряд

1.25

pronged

1.23

Activations Density 0.506%