INDEX

Explanations

introduces specifics

The neuron fires strongly on the CSS “border” token—especially in the “box-sizing: border-box” declarations.

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

its

-1.16

 voulons

-1.02

 todav

-0.99

或是

-0.98

それを

-0.98

 hingga

-0.98

 apartament

-0.97

示意图

-0.97

 hata

-0.94

lyte

-0.90

POSITIVE LOGITS

 opět

1.09

accro

1.06

IVEN

1.04

んじゃ

1.03

痈

1.01

siehe

1.00

Hilsen

1.00

 petróleo

0.99

 vytvoř

0.98

 errichtet

0.96

Activations Density 0.000%