INDEX

Explanations

common verbs and nouns

This neuron detects very common function words—particularly pronouns and determiners (e.g. “that,” “they,” “it,” “you,” “the”) and basic “to be” forms.

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

 exportación

-1.55

 each

-1.48

Läh

-1.31

but

-1.30

 läm

-1.24

 personalización

-1.22

 kök

-1.20

 ingenieros

-1.18

 venido

-1.17

 indústria

-1.17

POSITIVE LOGITS

(!__

1.47

万美元

1.43

 なら

1.29

亿美元

1.28

两者

1.20

盤

1.20

Trichlor

1.20

檠

1.19

its

1.17

 slick

1.17

Activations Density 0.051%