INDEX

Explanations

The neuron fires on named‐entity tokens (e.g. people’s names, place names, organization names, book/chapter references, dates, etc.).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

र्यंत

0.63

 보인다

0.61

\/}

0.60

린다

0.59

॑

0.59

 रक्षाबंधनाच्या

0.58

 प्रकल्

0.57

다라고

0.57

 पाण्याच्या

0.56

ôts

0.55

POSITIVE LOGITS

3.17

；

2.53

();

2.50

2.42

;//

2.42

؛

2.38

.;

2.34

!;

2.30

);

2.25

;}

2.22

Activations Density 0.344%