INDEX

Explanations

pronoun followed by communication

The neuron activates on numeric tokens (quantities, measurements, or figures).

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

-2.48

you

-2.42

-2.41

↵↵

-2.39

in

-2.38

or

-2.34

on

-2.22

There

-2.19

by

-2.19

and

-2.16

POSITIVE LOGITS

4.25

the

2.98

趿

2.53

注意事

2.38

 fournisseurs

2.30

︲

2.30

 emballage

2.28

粜

2.28

 fidé

2.22

 something

2.20

Activations Density 0.061%