INDEX

Explanations

tower, towers, towering

The neuron fires on any occurrence of the substring “tower” (in any casing or compound name), i.e. mentions of towers or “Tower” in proper nouns and sentences.

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

₶

-2.22

聶

-2.14

اتها

-2.11

Ἢ

-2.11

 McLaugh

-2.08

 voeren

-2.08

啸

-2.05

みてください

-2.05

ஂ

-2.03

りました

-2.02

POSITIVE LOGITS

';

2.86

</h3>

2.84

2.64

隳

2.50

</sub>

2.36

</blockquote>

2.33

 harten

2.25

</strong>

2.20

}$

2.17

 další

2.17

Activations Density 0.006%