INDEX

Explanations

roles played by actors

This neuron detects descriptive adjectives (especially positive or evocative character traits) that modify people or roles in film or stage contexts.

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

 nunc

-1.05

欤

-1.02

 électron

-1.02

 réfrig

-0.98

 Regie

-0.95

 gmin

-0.92

 ули

-0.92

 einzeln

-0.92

 contextLoads

-0.91

composed

-0.91

POSITIVE LOGITS

in

2.92

 from

1.77

 dalam

1.41

 during

1.30

 recientes

1.22

ใน

1.21

 във

1.13

of

1.10

 characters

1.07

 景色

1.07

Activations Density 0.070%