INDEX

Explanations

Amazon products and services

This neuron detects mentions of the company Amazon (and closely related Amazon‐branded terms).

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

薷

-1.64

,"

-1.64

,“

-1.60

,?

-1.59

出手

-1.51

 arabes

-1.47

⚐

-1.47

緑

-1.47

 باشه

-1.41

*{-

-1.41

POSITIVE LOGITS

We

1.91

 hatte

1.41

 What

1.39

できる

1.38

Dijo

1.37

ges

1.35

 stroj

1.34

 conflicto

1.33

τής

1.30

1.28

Activations Density 0.014%