INDEX

Explanations

military, sports, and political figures

The neuron primarily activates on words naming roles, positions, or organized groups (e.g. “starter,” “fleet,” “defenseman,” “troops,” “captain”).

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

of

-2.16

 because

-2.09

and

-2.05

his

-1.70

an

-1.41

for

-1.34

can

-1.32

as

-1.30

 your

-1.29

 Акаде

-1.29

POSITIVE LOGITS

wendige

1.34

 ピンク

1.28

orious

1.27

 poign

1.18

кою

1.18

Ꮕ

1.15

 excep

1.15

 posib

1.13

reo

1.13

 produrre

1.13

Activations Density 0.061%