INDEX

Explanations

towels, wipes, cloths

The neuron fires on names of household fabric items (napkins, towels, washcloths, wipes, 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

 pingente

-1.61

 แต่

-1.56

 جديدة

-1.54

 year

-1.41

錾

-1.39

 verdadeira

-1.38

But

-1.37

 boneco

-1.36

 folhe

-1.34

 igreja

-1.34

POSITIVE LOGITS

igten

1.52

volve

1.46

 ifølge

1.44

ouſly

1.38

čení

1.35

新款

1.33

嫺

1.30

ssing

1.30

キング

1.29

 решили

1.27

Activations Density 0.030%