INDEX

Explanations

verbs followed by prepositions/articles

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

our

-1.50

 буквально

-1.30

we

-1.27

 maybe

-1.23

 Maybe

-1.21

 même

-1.18

-1.16

стал

-1.16

乃至

-1.15

-1.13

POSITIVE LOGITS

」。

1.33

）。

1.28

”。

1.26

})

1.23

tualmente

1.20

ază

1.14

.}

1.12

 epoca

1.09

 Verenigde

1.07

but

1.06

Activations Density 0.095%