INDEX

Explanations

spatial relationships

The main thing this neuron does is detect numeric tokens (e.g., years, measurements, and other numbers).

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

 with

-1.60

and

-1.35

our

-1.18

 that

-1.16

for

-1.15

 dengan

-1.13

 حالی

-1.07

so

-1.05

Nuorodos

-1.05

 especially

-1.03

POSITIVE LOGITS

 behind

2.78

 beneath

2.55

 beside

2.28

 underneath

2.28

 below

2.14

Behind

2.06

 above

2.05

behind

2.02

 Behind

1.94

Beneath

1.81

Activations Density 0.113%