INDEX

Explanations

color values like (0,0,0) or rgb

The neuron never fires (all activations are zero), i.e. it’s a “dead” neuron that doesn’t detect any pattern.

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

Œ

-1.28

 ofte

-1.23

-1.21

الت

-1.20

 hisz

-1.20

chait

-1.17

ſelf

-1.17

Character

-1.15

 sied

-1.15

-1.14

POSITIVE LOGITS

and

1.65

Motto

1.36

 mehrere

1.16

Ilustra

1.13

Glit

1.11

 their

1.10

Puss

1.09

 edilen

1.08

 zahlreiche

1.07

 dieselben

1.07

Activations Density 0.006%