INDEX

Explanations

Name and author

This neuron detects parenthesized occupational or role labels (e.g. “(author)”, “(judge)”, “(writer)”) following person names.

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

 because

-1.88

↵↵

-1.77

-1.59

an

-1.57

 these

-1.54

 These

-1.34

These

-1.30

Being

-1.20

if

-1.20

POSITIVE LOGITS

 ujedno

1.59

 سيكون

1.48

使って

1.43

 considérer

1.38

 Спасибо

1.36

cribir

1.35

enablog

1.35

เลือก

1.30

 Tất

1.30

Viitteet

1.30

Activations Density 0.009%