INDEX

Explanations

nearness and proximity

This neuron detects words that express physical closeness or nearness, such as “close,” “proximity,” or “near.”

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

-1.52

 name

-1.35

-1.34

-1.30

 Betrach

-1.23

 solches

-1.22

 Miß

-1.20

 Terbaik

-1.17

 الرسم

-1.13

pci

-1.12

POSITIVE LOGITS

änemark

1.45

 narkoba

1.34

cuado

1.25

Цитата

1.24

 heran

1.22

étricas

1.21

肌肤

1.21

近づ

1.20

 еще

1.18

 condicionado

1.16

Activations Density 0.078%