INDEX

Explanations

when... or around.

The neuron strongly activates on numeric tokens (digits or numbers) in the text.

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

-2.20

-1.80

</h2>

-1.80

-1.71

was

-1.61

}{

-1.59

 With

-1.58

-1.57

 That

-1.55

up

-1.53

POSITIVE LOGITS

踅

2.06

趿

2.03

 dezelve

1.95

 libere

1.94

 kutoka

1.88

 イラストレーション

1.82

 houſe

1.80



1.77

袿

1.75

 sirena

1.73

Activations Density 0.005%