INDEX

Explanations

acting roles

This neuron detects mentions of actors’ roles (e.g., “role” or “roles” in a film or production).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

🧌

-1.46

蹀

-1.41

蓥

-1.39

Ĝ

-1.38

 diámetro

-1.38

-1.37

骓

-1.37

*/

-1.37

 prace

-1.36

tyd

-1.33

POSITIVE LOGITS

tisgarh

1.76

わかった

1.62

ときの

1.58

悲しい

1.53

 nears

1.50

皷

1.50

nouveau

1.42

isations

1.39

 lures

1.38

 tendrá

1.38

Activations Density 0.015%