INDEX

Explanations

possessive pronouns followed by a noun

The neuron activates on possessive pronouns (e.g., “his,” “its”) indicating ownership.

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

 vegetación

-1.55

and

-1.50

 exportación

-1.44

 núm

-1.42

 âges

-1.38

 utilisons

-1.36

 artesanía

-1.34

舠

-1.32

 lámina

-1.32

႐

-1.31

POSITIVE LOGITS

own

1.77

1.61

 tudi

1.27

逡

1.23

に対応

1.23

of

1.22

 MÁS

1.21

 with

1.19

ectado

1.19

 SOBRE

1.18

Activations Density 0.070%