INDEX

Explanations

mathematical properties and theorems

The neuron fires on technical mathematical phrases stating problems or results—especially terms like “norm,” “bounds,” “sharp,” and related language introducing a theorem or estimate.

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

這些

-1.37

ícias

-1.37

 vorhandenen

-1.34

 immediately

-1.34

かは

-1.33

 vegetación

-1.28

內的

-1.27

 maceta

-1.24

 incendios

-1.21

 ventilación

-1.20

POSITIVE LOGITS

of

1.67

 also

1.66

and

1.61

in

1.58

for

1.57

 even

1.57

 sogar

1.48

 одежда

1.38

 Neither

1.38

 privat

1.36

Activations Density 0.514%