INDEX

Explanations

Player.king

The neuron activates on occurrences of the word “Player.”

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

</strong>

-1.21

</em>

-1.20

</h4>

-1.09

 Histor

-1.07

-1.06

-1.05

↵

-1.05

 obwohl

-1.04

-1.00

<em>

-1.00

POSITIVE LOGITS

pierw

1.24

arXiv

1.19

 ISLANDS

1.16

ᕱ

1.15

Knowledge

1.15

 gaji

1.13

 zilver

1.10

prefs

1.09

"$

1.09

dass

1.09

Activations Density 0.025%