INDEX

Explanations

conditions and trials

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

Doesn

-1.27

Wouldn

-1.23

)$.

-1.20

doesn

-1.16

 \%$.

-1.14

んだから

-1.14

)++;

-1.13

wouldn

-1.13

 meski

-1.12

sistence

-1.11

POSITIVE LOGITS

was

4.28

is

3.56

 were

2.34

 был

2.08

 была

2.06

 было

2.05

was

2.02

has

2.00

 được

1.93

are

1.67

Activations Density 0.722%