INDEX

Explanations

rise or fall

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

 когато

-1.59

 they

-1.50

itoneum

-1.49

 Italijanski

-1.45

 трябва

-1.44

 then

-1.43

 Evidence

-1.42

灕

-1.42

 soldadura

-1.38

 zimowe

-1.37

POSITIVE LOGITS

 what

1.47

 accustomed

1.41

 VEGET

1.34

臯

1.32

 while

1.31

続く

1.30

 publice

1.28

1.26

 يحدث

1.25

"$

1.22

Activations Density 0.026%