INDEX

Explanations

legal citations or URLs

This neuron activates on snippets of source code—especially Java keywords, class/method names, punctuation, and other code‐specific tokens.

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

 their

-1.80

it

-1.53

 encanto

-1.50

 only

-1.49

its

-1.48

 would

-1.46

all

-1.42

 they

-1.29

iteln

-1.24

 there

-1.20

POSITIVE LOGITS

 unseres

1.41

 также

1.34

 обычно

1.27

 プリント

1.27

 unserer

1.27

Hilsen

1.20

 firs

1.20

drücke

1.19

Steg

1.18

remacy

1.18

Activations Density 0.003%