INDEX

Explanations

official statements

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 spokesperson

-2.22

 spokesman

-2.14

 Spokes

-1.95

 spokeswoman

-1.92

 spokespersons

-1.48

 spokes

-1.45

Spo

-1.15

 portavoz

-0.99

spo

-0.93

 representative

-0.82

POSITIVE LOGITS

 garantiza

0.57

 OFDb

0.48

for

0.45

 umane

0.44

iness

0.44

 manquer

0.43

 umana

0.42

anship

0.42

ädie

0.42

nél

0.41

Activations Density 0.005%