INDEX

Explanations

figure 1

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

the

-1.78

by

-1.67

},

-1.55

 other

-1.53

 другие

-1.40

 wysokość

-1.38

 других

-1.38

 einzelne

-1.35

Карьера

-1.34

 become

-1.32

POSITIVE LOGITS

Ecotoxicity

1.38

 izvē

1.24

続

1.23

是在

1.22

 tege

1.21

草莓

1.20

 animosity

1.20

 geforce

1.20

ALTH

1.18

 indien

1.17

Activations Density 0.151%