INDEX

Explanations

comments with license disclaimers

The neuron activates on any numeric token (digits or numbers), such as version or year figures, wherever they appear.

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

”:

-1.88

↵

-1.77

鍍

-1.76

 plethora

-1.73

 erfaren

-1.69

Продам

-1.67

 själ

-1.65

 various

-1.63

)’

-1.59

 möjlighet

-1.59

POSITIVE LOGITS

 which

2.50

and

2.22

 where

2.02

 then

1.98

},

1.90

 abgerufen

1.74

but

1.73

1.72

掛けて

1.64

umerable

1.63

Activations Density 0.041%