INDEX

Explanations

specific beginnings

The neuron strongly activates on English personal pronouns (e.g. I, us, He).

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

 также

-1.38

 επίσης

-1.20

ѝ

-1.17

 tantangan

-1.13

 ebenfalls

-1.12

 نیز

-1.12

וּ

-1.11

このような

-1.10

 OGSÅ

-1.09

our

-1.06

POSITIVE LOGITS

mathrm

1.19

 принял

1.13

 ought

1.13

 teneur

1.05

你要

1.04

 doesn

1.03

jusqu

1.02

訫

1.02

</tbody>

1.02

 disponibilité

1.01

Activations Density 0.000%