INDEX

Explanations

word endings for names

The neuron detects fragments of capitalized proper names or named entities (person, place, or title).

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

几个月

-2.16



-2.14

 sogen

-2.13

的态度

-2.13

 Artículos

-2.05

的情绪

-2.05

 وفي

-2.05

见状

-2.02

 zusätz

-1.98

 unangemess

-1.98

POSITIVE LOGITS

</th>

2.64

</h1>

2.56

↵↵

2.50

捭

2.42

</u>

2.34

}$

2.28

 Перейти

2.23

piecze

2.20

2.19

</i>

2.14

Activations Density 0.353%