INDEX

Explanations

weigh in or say

The neuron activates on phrasal verbs that consist of a verb immediately followed by “in” (e.g. “weigh in,” “chime in,” “wade in,” “chip in,” etc.).

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

-1.80

-1.51

we

-1.46

—

-1.41

うた

-1.34

 abiertos

-1.31

ถ

-1.30

はじめ

-1.29

 expect

-1.29

 They

-1.26

POSITIVE LOGITS

ども

1.75

 about

1.43

妧

1.40

Kegiatan

1.40

高雄

1.39

 includ

1.38

颼

1.37

荜

1.36

bleib

1.35

 мнение

1.34

Activations Density 0.014%