INDEX

Explanations

what you see

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

 ингреди

-1.35

 also

-1.20

 this

-1.13

for

-1.12

 подходя

-1.08

 because

-1.06

 quando

-1.05

 rowspan

-1.03

 many

-1.02

 specific

-1.02

POSITIVE LOGITS

 tevreden

1.41

 uſe

1.20

 SIZES

1.19

 WALTZ

1.17

 皮肤

1.17

亵

1.16

消失了

1.16

uſ

1.14

helloworld

1.13

 দেখ

1.12

Activations Density 0.054%