INDEX

Explanations

machine learning code and general text

The neuron strongly activates on mentions of neural‐network layer class names (e.g. “Dense,” “Conv3D,” “BatchNormalization,” etc.).

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

-1.82

))

-1.59

 "/";

-1.45

ol

-1.45

 bevor

-1.35

]]=

-1.35

 são

-1.33

our

-1.31

 anunciado

-1.28

POSITIVE LOGITS

tovat

1.37

uju

1.32

 something

1.30

رير

1.30

 beſ

1.29

 Désolé

1.29

jugador

1.28

 strumenti

1.28

 بتوان

1.27

 alimenti

1.27

Activations Density 0.002%