INDEX

Explanations

numbers, ratings, scores

The neuron strongly activates on standalone numeric tokens (digits and simple 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

 ukraine

-1.16

pergillus

-1.16

 célé

-1.16

 ketones

-1.15



-1.14



-1.13

machte

-1.12

 nélk

-1.12

 Процитовано

-1.11

każ

-1.10

POSITIVE LOGITS

to

1.39

it

1.25

had

1.17

1.16

1.15

as

1.15

In

1.14

re

1.11

two

1.06

with

1.06

Activations Density 0.058%