INDEX

Explanations

add, put, add-header, add-cell

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

 vorige

-1.66

なども

-1.57

 ferien

-1.35

 tirs

-1.34

はある

-1.33

 kompak

-1.31

 maler

-1.26

 seseorang

-1.25

などが

-1.23

seks

-1.21

POSITIVE LOGITS

 unangemessene

1.48

());

1.47

 beeintr

1.39

('

1.33

 Eigentü

1.31

</b>

1.29

1.27

())));

1.25

 więc

1.24

()">

1.24

Activations Density 0.005%