INDEX

Explanations

conference calls and phone conversations

The neuron fires on terms referring to telephone‐based meetings or calls (e.g. “phone,” “call,” “conference call,” “conference,” “calls,” “conferencing”).

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

 eigene

-1.39

↵

-1.37

’

-1.33

“

-1.27

 красивый

-1.27

ｨ

-1.23

Története

-1.19

 poprzez

-1.18

趣

-1.18

蒙古

-1.17

POSITIVE LOGITS

 they

1.47

anship

1.40

烔

1.36

჻

1.30

panning

1.29

řízen

1.29

他们是

1.29

抔

1.29

ём

1.23

imir

1.22

Activations Density 0.014%