INDEX

Explanations

technical enumerations or choices

The neuron fires on individual items in enumerated lists of technical terms or specific examples.

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

 then

-1.34

ecznie

-1.27

 JADX

-1.27

ьа

-1.19

flox

-1.18

 sientes

-1.16

 católica

-1.12

ningen

-1.11

 ensuing

-1.11

POSITIVE LOGITS

or

2.25

 или

1.84

或

1.73

หรือ

1.64

 hoặc

1.50

 desmotiv

1.43

或者

1.42

llac

1.41

 peores

1.38

이나

1.37

Activations Density 0.271%