INDEX

Explanations

phone numbers

The neuron strongly activates on consecutive numeric digits (e.g. phone‐number sequences).

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

 baile

-1.42

 surgiu

-1.34

></

-1.34

点此

-1.30

を活用

-1.30

 trouxe

-1.27

 decidiu

-1.27

etí

-1.27

əsi

-1.26

>()

-1.25

POSITIVE LOGITS

1.43

at

1.38

they

1.30

́s

1.27

 veröffentlicht

1.25

 Sortiment

1.25

1.23

 cuarzo

1.23

Told

1.23

*',

1.23

Activations Density 0.003%