INDEX

Explanations

courage and bravery

This neuron detects words expressing courage or bravery (e.g., “brave,” “bold,” “courage,” “fearless”).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

フー

0.61

🤌

0.59

 రూప

0.58

ոն

0.57

าลัย

0.57

🫠

0.55

 preoccupied

0.55

 preoccup

0.54

ributive

0.54

 reminders

0.54

POSITIVE LOGITS

 courage

2.66

 courageous

2.52

 brave

2.50

 bravery

2.41

 boldness

2.38

 daring

2.36

 bravely

2.31

 bold

2.22

勇敢

2.22

勇

2.22

Activations Density 0.639%