INDEX

Explanations

end punctuation and leading pronouns

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

 denna

-1.27

struzioni

-1.20

 này

-1.20

 aquest

-1.16

 proceedings

-1.10

 this

-1.04

✅

-1.03

.)-

-1.02

 detta

-1.02

 contento

-1.02

POSITIVE LOGITS

2.67

we

2.09

my

1.97

 myself

1.49

our

1.45

 really

1.34

 আম

1.31

вими

1.29

 naše

1.29

 μας

1.28

Activations Density 0.005%