INDEX

Explanations

grey or gray

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

 cheiro

-0.87

principal

-0.86

 concentrado

-0.82

 vítima

-0.80

 empreg

-0.77

 dàng

-0.76

 raggiunto

-0.75

servez

-0.75

 dryers

-0.75

 Avon

-0.74

POSITIVE LOGITS

hound

1.43

 matter

1.22

matter

1.01

 Grey

0.98

SCALE

0.95

Matter

0.92

 Gray

0.91

 eminence

0.89

Grey

0.88

 scale

0.87

Activations Density 0.012%