INDEX

Explanations

mathematical notation and equations

The neuron detects standalone numeric tokens (digits, decimals, equation numbers, and similar number‐like symbols) within mathematical formulae.

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

bestos

-1.59

 Souver

-1.56

}))

-1.54

･･

-1.53

(*^^

-1.48

＼(^

-1.46

Schule

-1.45

 Khusus

-1.45

 потім

-1.44

corbic

-1.41

POSITIVE LOGITS

↵

1.81

1.55

new

1.52

te

1.48

↵↵↵

1.39

来

1.36

</h3>

1.35

ti

1.34

 גם

1.34

 trennen

1.33

Activations Density 0.011%