INDEX

Explanations

noun followed by is or are

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

 zullen

-1.44

 نے

-1.42

她就

-1.34

 должны

-1.31

 kellett

-1.27

 đã

-1.23

 उन्होंने

-1.21

seemed

-1.16

 geeft

-1.14

 geldt

-1.13

POSITIVE LOGITS

is

4.25

are

2.73

 được

2.63

 vengono

2.45

被

2.14

 wordt

1.97

 wird

1.91

 being

1.85

 gets

1.80

 zostać

1.70

Activations Density 0.570%