INDEX

Explanations

profit, publicity, and votes

The neuron detects references to monetary gain or profit (e.g., words about making money, profits, sales, or financial interests).

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

 your

-1.45

 sodio

-1.16

ficit

-1.15

 Ihren

-1.14

今でも

-1.11

 proveniente

-1.09

 مباراة

-1.09

この時期

-1.09

 baixa

-1.06

 frequentemente

-1.06

POSITIVE LOGITS

 cuando

1.26

 when

1.26

----------

1.23

 върху

1.19

 have

1.15

ส่วน

1.15

ísimas

1.14

 never

1.13

 rather

1.11

 عندما

1.10

Activations Density 0.094%