INDEX

Explanations

item in html class names

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

iální

-1.55

 επίσης

-1.53

 גם

-1.48

 också

-1.45

laşı

-1.42

等は

-1.40

also

-1.38

četně

-1.36

);

-1.34

 réinitial

-1.34

POSITIVE LOGITS

 <=",

1.50

)--(

1.45

 noting

1.41

]=>

1.38

denk

1.34

1.33

重要的是

1.31

;%%

1.30

ibrator

1.30

adé

1.29

Activations Density 0.010%