INDEX

Explanations

css dimensions

This neuron detects numeric literals used in CSS style rules, especially pixel-based size values.

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

one

-1.36

 could

-1.30

as

-1.28

for

-1.25

Ų

-1.23

 eight

-1.23

can

-1.22

 these

-1.19

 before

-1.16

 this

-1.13

POSITIVE LOGITS

泐

1.22

atique

1.17

を探す

1.16



1.12

 („

1.11

zość

1.08

 trouva

1.08

 constater

1.08

llingen

1.07

 människor

1.05

Activations Density 0.013%