INDEX

Explanations

No Explanations Found

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

 their

-1.33

ſelves

-1.20

 them

-1.20

 Dioxide

-1.19

↑↑↑</

-1.18

 którzy

-1.17

」，

-1.16

 this

-1.16

 retrovisor

-1.14

こだわ

-1.13

POSITIVE LOGITS

1.34

again

1.29

mería

1.20

 Uncertain

1.17

et

1.14

—

1.13

IN

1.11

邰

1.11

another

1.10

飙

1.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.