INDEX

Explanations

neural network components and context identifiers

The neuron strongly activates on mentions of “encoder” (especially in “autoencoder”) and related model components like “decoder.”

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

 oogen

-1.47

 they

-1.31

 lorenzo

-1.30

 手順

-1.30

麃

-1.29

 imbal

-1.27

 lada

-1.27

 alberi

-1.27

正確

-1.26

Nc

-1.26

POSITIVE LOGITS

")

1.58

cbd

1.51

()],

1.50

()]);

1.48

 todas

1.45

//}

1.45

1.44

ſelves

1.42

()])

1.39

 singles

1.34

Activations Density 0.009%