INDEX

Explanations

available or acceptable

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

 gän

-1.03

improved

-0.96

peat

-0.88

geführt

-0.87

 belangrijke

-0.87

 nigdy

-0.85

 kwaliteit

-0.85

 verbeter

-0.84

 ilmo

-0.83

ร์

-0.83

POSITIVE LOGITS

 available

1.26

 acceptable

1.22

 permissible

1.19

 exempted

1.16

 tolerated

1.16

 allowable

1.07

 allowed

1.02

 tolerate

1.01

 doable

1.00

 pels

1.00

Activations Density 0.068%