INDEX

Explanations

specific cases

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

 doInBackground

-0.62

 cargo

-0.61

FontOfSize

-0.58

ftagPool

-0.55

aines

-0.52

perry

-0.51

 spite

-0.50

opposed

-0.50

atify

-0.50

 Eisenberg

-0.50

POSITIVE LOGITS

 houſe

1.08

 Diſ

1.05

 Anſ

1.02

 Houſe

1.02

 myſelf

0.94

 Jefus

0.93

 Conſ

0.93

 Majefty

0.92

 greateſt

0.88

 Reſ

0.87

Activations Density 0.050%