INDEX

Explanations

when describing a condition

The neuron strongly detects occurrences of the conjunction “When,” especially at the start of a new sentence or clause.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.40

ação

1.30

1.27

в

1.27

ból

1.24

1.23

 মজুমদার

1.16

idagi

1.15

هاي

1.15

dzi

1.14

POSITIVE LOGITS

soever

2.02

 xưa

1.37

마다

1.30

 adduct

1.22

쯤

1.20

事人

1.12

ी

1.09

hydroxyl

1.06

 وعند

1.05

numbered

1.02

Activations Density 0.078%