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

 would

-1.23

Você

-1.17

США

-1.13

陕西

-1.03

 кровать

-1.03

 technik

-1.02

Ketika

-1.02

مدیر

-1.02

 évé

-1.01

 tabak

-1.01

POSITIVE LOGITS

 including

1.20

 klicken

1.13

 Matthew

1.02

 terceiro

1.02

 amongst

1.01

場面

1.00

 zweiter

1.00

 ehemal

0.99

 family

0.98

Don

0.98

Activations Density 0.000%

No Known Activations

This feature has no known activations.