INDEX

Explanations

foreign words or concepts

The neuron flags the key topic words (the main subject-specific content terms) in each passage.

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

unno

-1.14

Миха

-1.04

 Zent

-1.03

ẨM

-1.02

örd

-1.02

 HAPPENED

-1.01

 herv

-0.99

Джере

-0.99

 transmettre

-0.98

Américaine

-0.97

POSITIVE LOGITS

 tragé

1.48

 luxus

1.41

 cortina

1.38

 kabát

1.36

 corda

1.31

 pán

1.28

 inappropriés

1.27

 lampada

1.26

veu

1.26

 bobina

1.25

Activations Density 0.055%