INDEX

Explanations

conditions, possibilities, and allowances

The neuron primarily detects numerical tokens and numeric expressions (e.g. digits, multi‐digit numbers, or numbers with decimals).

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

 they

-1.64

 marea

-1.39

 cioc

-1.38

 either

-1.38

=’

-1.35

 magazin

-1.32

 apartament

-1.30

 barat

-1.30

 then

-1.23

=“

-1.23

POSITIVE LOGITS

戻る

1.20

 yine

1.19

one

1.15

อีก

1.13

 एक

1.13

 wieder

1.13

 моих

1.12

玉米

1.10

返す

1.05

 form

1.04

Activations Density 0.030%