INDEX

Explanations

Yes/No answers

The neuron fires on single-word “Yes” or “No” answers at the start of a response.

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

to

-2.36

of

-2.23

an

-1.70

now

-1.66

 even

-1.64

on

-1.57

at

-1.55

any

-1.52

for

-1.50

-1.49

POSITIVE LOGITS

 ecológica

1.59

 burbujas

1.52

 doméstica

1.48

 pintados

1.45

 energética

1.45

 Werkstatt

1.44

 particularmente

1.42

 líquida

1.41

 durabilidad

1.41

 cristales

1.37

Activations Density 0.028%