INDEX

Explanations

not only... but also

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

 although

-2.55

 however

-2.45

 однако

-2.30

yet

-2.28

 όμως

-2.25

 jednak

-2.09

}$.

-1.98

 però

-1.94

 nonetheless

-1.93

 však

-1.91

POSITIVE LOGITS

 بلکه

2.30

 sondern

2.09

 sino

1.42

1.40

itself

1.33

 utan

1.30

 tjen

1.26

 kapak

1.25

también

1.24

likace

1.24

Activations Density 0.034%