INDEX

Explanations

[descriptor] [related noun]

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

}$.

-1.39

%.

-1.36

)$.

-1.35

 потому

-1.31

}),

-1.28

 because

-1.27

 when

-1.25

()),

-1.23

 which

-1.22

any

-1.22

POSITIVE LOGITS

はその

1.09

である

1.04

 couldn

1.04

ELA

1.02

れていた

1.02

ButtonClicked

1.00

RILL

0.99

 ين

0.98

اری

0.98

ptăm

0.96

Activations Density 0.127%