INDEX

Explanations

introducing an explanation or process

The neuron is strongly activated by first‐person plural references (especially “we” and related usages).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 मुझे

1.53

 আমাকে

1.46

my

1.45

मुझे

1.39

 मुझसे

1.38

 tôi

1.37

 мне

1.34

 saya

1.33

 مجھے

1.32

私の

1.31

POSITIVE LOGITS

 ourselves

2.70

 आहोत

2.03

 هستیم

1.96

 можем

1.94

 знаем

1.86

 છીએ

1.84

ходим

1.84

 داریم

1.80

 хотим

1.80

 ediyoruz

1.77

Activations Density 1.292%