INDEX

Explanations

soap opera

The neuron detects mentions of soap operas (the term “soap opera” or specific soap‐opera titles).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-1.66

you

-1.46

The

-1.44

 passenden

-1.35

 grossen

-1.34

 technology

-1.32

-1.29

 Think

-1.27

...

-1.25

 nowy

-1.23

POSITIVE LOGITS

錞

1.54

Organiser

1.42



1.34

 kompeti

1.31

Eleg

1.30

INTRODUCCIÓN

1.26

Dolphin

1.24

 müh

1.23

currPos

1.21

STUDIES

1.20

Activations Density 0.016%