INDEX

Explanations

active state or component

This neuron detects occurrences of the adjective “active” when used in technical or scientific contexts (e.g., “active regions,” “active catalyst,” “active sites”).

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

-1.20

培训

-1.18

 beide

-1.16

 Priv

-1.13

vaded

-1.12

erg

-1.11

elsch

-1.10

纽

-1.08

 acceso

-1.08

Comes

-1.05

POSITIVE LOGITS

 entanto

1.27

ումներ

1.27

 soñar

1.25

امية

1.24

 that

1.24

 pouze

1.23

Pozri

1.23

sbereich

1.22

偸

1.20

 muchísimo

1.20

Activations Density 0.112%