INDEX

Explanations

solidarity and relations

The main thing this neuron does is detect the word “solidarity” (and its high-activation variants) in text.

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

-2.28

 There

-2.25

ть

-2.17

 With

-2.16

 These

-2.11

 सभी

-2.11

してしまった

-2.06

The

-2.02

 seine

-2.00

POSITIVE LOGITS

肏

2.25

рби

2.25

嗵

2.23

︲

2.17

 イラストレーション

2.13

 qualit

2.09

⦊

2.08

 sufic

2.06

氽

2.06

ский

2.05

Activations Density 0.002%