INDEX

Explanations

You are possessive or descriptive

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

着一个

-2.34

for

-1.92

 while

-1.88

了一個

-1.81

着一

-1.68

to

-1.67

“

-1.65

着自己的

-1.60

攫

-1.59

two

-1.53

POSITIVE LOGITS

you

1.83

 nasze

1.64

we

1.60

 wszystkie

1.58

 nasz

1.52

our

1.51

 your

1.48

ないし

1.46

戗

1.45

lizes

1.45

Activations Density 0.298%