INDEX

Explanations

car, driving, vehicles, automobiles

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

Lod

-0.09

elson

-0.09

Kro

-0.09

kos

-0.09

Ven

-0.08

lain

-0.08

 proces

-0.08

.dart

-0.08

tee

-0.08

 Toshiba

-0.08

POSITIVE LOGITS

 parked

0.16

 vehicle

0.14

 vehicles

0.13

riages

0.13

 cars

0.12

car

0.11

/tr

0.11

.drive

0.11

(vehicle

0.11

ibbean

0.11

Activations Density 1.576%