INDEX

Explanations

license requirements

The neuron activates on the token “must,” flagging obligation statements (e.g., in license or specification texts).

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

 vorigen

-2.77

蹰

-2.48

,..

-2.48

 triomphe

-2.47

ências

-2.41

 کیا

-2.31

 früheren

-2.30

茈

-2.25



-2.25

 möglichen

-2.23

POSITIVE LOGITS

鹮

2.53

be

2.52

ྜ

2.41

м

2.38

</td>

2.31

[]);

2.23

𖥧

2.22

Its

2.19

要在

2.19

Activations Density 0.031%