INDEX

Explanations

certification exams

The neuron strongly activates on numeric tokens and numerals (including dates, scores, decimal values, and other number-like expressions).

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

说不定

-1.34

等我

-1.31

 vôtre

-1.26

是想

-1.24

 Bogotá

-1.23

árbol

-1.20

請繼續

-1.20

 nuove

-1.19

 BEAUT

-1.17

큰

-1.16

POSITIVE LOGITS

 exam

1.42

on

1.30

 exams

1.28

]^{-

1.24

an

1.23

Ⅵ

1.23

🫓

1.20

')))

1.18

ｰ

1.15

so

1.14

Activations Density 0.034%