INDEX

Explanations

emotions and feelings

The neuron detects words and phrases that signal emotional impact or evoke feelings (e.g., “emotions,” “feelings,” “stirring,” “tugs at the heartstrings,” “nostalgic,” “evoking”).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

including

-1.64

<h3>

-1.45

Either

-1.41

 mettre

-1.40

either

-1.36

example

-1.35

 actuelles

-1.34

 hermé

-1.27

via

-1.27

please

-1.24

POSITIVE LOGITS

and

1.53

of

1.47

 aquellas

1.42

 know

1.37

by

1.36

 also

1.31

]?.

1.27

all

1.27

ADELPHIA

1.27

Etimología

1.26

Activations Density 0.028%