INDEX

Explanations

enable or disable

The neuron is detecting common English function words (stopwords) such as “to,” “of,” “the,” “be,” and similar prepositions/articles in technical documentation.

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

 этих

-1.43

vonne

-1.34

bsen

-1.28

ḿ

-1.25

ícias

-1.24

vermectin

-1.22

laria

-1.21

carus

-1.20

也在

-1.20

方は

-1.20

POSITIVE LOGITS

 from

1.68

for

1.42

 with

1.36

in

1.28

 ALWAYS

1.18

年後

1.16

 after

1.13

on

1.11

:{

1.11

 when

1.09

Activations Density 0.051%