INDEX

Explanations

knights and Sir

The neuron activates on terms referring to knighthood, such as “knight,” “knights,” “Sir,” or “chivalry.”

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

</em>

-2.11

戬

-1.91

</h4>

-1.60

渇

-1.54

悪魔

-1.51

𖤍

-1.49

INOIS

-1.45

交渉

-1.45

 japoneses

-1.42

POSITIVE LOGITS

</i>

1.98

We

1.59

}$

1.56

 возникает

1.54

 dubbed

1.51

According

1.50

一身

1.49

しないと

1.46

</h1>

1.45

Only

1.44

Activations Density 0.032%