INDEX

Explanations

conjunctions and negation

The neuron is specialized in detecting numeric tokens (digits and 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

 также

-2.03

 також

-1.55

 данной

-1.48

 również

-1.46

流石

-1.38

このような

-1.35

 également

-1.30

 данного

-1.27

ỡi

-1.27

 therefore

-1.25

POSITIVE LOGITS

But

1.48

but

1.43

And

1.28

 entreg

1.23

 miljoen

1.20

 dispatched

1.17

grees

1.16

ᐈ

1.16

だが

1.14

not

1.12

Activations Density 0.071%