INDEX

Explanations

others

The neuron specifically fires on occurrences of the word “others,” i.e. references to “others.”

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

at

-2.55

}$

-2.52

齮

-2.17

ྂ

-2.08

 sont

-2.08

鏇

-2.06

鲥

-2.06

 sfer

-2.05

</b>

-2.03

‌ها

-2.03

POSITIVE LOGITS

та

2.59

</h3>

2.44

worldly

2.42

 bestimmten

2.41

नलोड

2.34

rentiel

2.28

马逊

2.27

羂

2.25

 besök

2.25

 besonderen

2.22

Activations Density 0.011%