INDEX

Explanations

metaphors and analogies

The neuron detects occurrences of the word “metaphor” (and its morphological variants such as “metaphors,” “metaphoric,” “meta- phor,” 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

Certain

-1.30

优秀

-1.29

-1.25

 специ

-1.22

冠军

-1.21

 exemplary

-1.20

柃

-1.20

技術

-1.20

rschein

-1.18

ка

-1.17

POSITIVE LOGITS

 Tonnen

1.48

ጵ

1.44

of

1.41

快要

1.28

FTW

1.27

 kampen

1.20

nyard

1.20

 tutup

1.20

osť

1.20

 loob

1.19

Activations Density 0.015%