INDEX

Explanations

historical and literary figures

This neuron detects personal names or other proper nouns referring to individuals.

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

in

-1.72

for

-1.65

 from

-1.46

 with

-1.35

Exeunt

-1.34

Negro

-1.27

着一个

-1.24

 merkezi

-1.21

িতে

-1.17

的气息

-1.16

POSITIVE LOGITS

 that

1.45

 nastro

1.45

 almofada

1.41

 moldura

1.37

 leopardo

1.34

 mascarilla

1.33

 tapete

1.31

 avevo

1.30

蚰

1.27

 couro

1.27

Activations Density 0.092%