INDEX

Explanations

defines or expresses formulas

The neuron detects definitional or formula‐introduction phrases (e.g. “is defined as,” “as follows,” “the following formula,” “looks like,” “can be described as”).

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

所有人都

-1.20

Ã

-1.11

abinieri

-1.10

 exceptionally

-1.09

 alcune

-1.06

 alcuni

-1.06

gier

-1.05

–

-1.03

●

-1.01

になっている

-1.01

POSITIVE LOGITS

 with

1.44

🔽

1.28

 unrelenting

1.20

 after

1.18

 without

1.16

 manzanas

1.16

 älskar

1.15

Following

1.13

 playful

1.13

 enticing

1.13

Activations Density 0.007%