INDEX

Explanations

words and phrases

The neuron detects first-person singular references (the pronoun “I,” especially in personal statements).

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

-1.44

があり

-1.22

 after

-1.20

marzo

-1.17

一品

-1.16

其

-1.16

 السياس

-1.13

 плата

-1.12

propyl

-1.11

 동안

-1.11

POSITIVE LOGITS

Variante

1.31

 lentejuelas

1.30

Fakta

1.30

を読む

1.27

を書く

1.26

...»

1.23

の詳細

1.22

materialien

1.22

nější

1.21

Paket

1.20

Activations Density 0.065%