INDEX

Explanations

full names

The neuron detects occurrences of personal names (capitalized first names) in the text.

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

and

-1.81

 with

-1.66

by

-1.63

as

-1.62

 listopada

-1.61

晅

-1.56

 czerwca

-1.53

縹

-1.52

 lutego

-1.51

ஂ

-1.47

POSITIVE LOGITS

to

1.71

 gän

1.52

 beschrieben

1.48

甗

1.41

 اقتصادی

1.41

↵↵

1.40

 alluring

1.40

殽

1.38

The

1.35

 dando

1.34

Activations Density 0.123%