INDEX

Explanations

united

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

united

-1.23

 united

-1.21

United

-1.18

 UNITED

-1.08

 United

-0.95

UNITED

-0.89

 ujednoznacz

-0.84

 oxygen

-0.81

 advanced

-0.81

oxygen

-0.77

POSITIVE LOGITS

 States

0.72

GOTREF

0.64

SequentialGroup

0.63

kheim

0.56

riwal

0.55

itects

0.53

')));

0.53

InputTagHelper

0.52

ristmas

0.52

 STATES

0.51

Activations Density 1.583%