INDEX

Explanations

quantity or certainty

The neuron flags individual proper names and other named entities (e.g. people, brands, titles).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 też

0.84

だ

0.78

 Sometimes

0.77

だから

0.76

 треба

0.75

 тоже

0.74

把

0.74

 درباره

0.72

 soms

0.72

 Might

0.71

POSITIVE LOGITS

非常的

1.52

非常に

1.24

 oldukça

1.20

 alot

1.19

utilizzo

1.09

 utilizes

1.06

 काफी

1.05

 굉장히

1.05

 אשר

1.04

 পরবর্তীতে

1.02

Activations Density 0.268%