INDEX

Explanations

pop culture

The neuron activates specifically on mentions of “pop culture,” detecting that exact reference in text.

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

 certainly

-1.35

 Certainly

-1.24

 With

-1.23

 particularly

-1.22

っていると

-1.19

 caprice

-1.17

 such

-1.16

 which

-1.12

 chiefly

-1.11

なるべく

-1.10

POSITIVE LOGITS

'");

1.62

signable

1.45

 biasa

1.43

gebir

1.35

energie

1.35

𓆏

1.34

statistik

1.34

 sempat

1.32

 Souhaitez

1.30

𖧵

1.30

Activations Density 0.197%