INDEX

Explanations

path and trail descriptions

The neuron activates on terms denoting walking routes or pathways (e.g., “path,” “trail,” “ridge,” “sidewalk”).

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

One

-1.49

↵

-1.46

’

-1.45

</h2>

-1.42

of

-1.38

})

-1.35

那里

-1.33

 that

-1.33

-1.32

 bersama

-1.31

POSITIVE LOGITS

 cuándo

1.53

Hyg

1.52

܆

1.48

 interwoven

1.43

 Empieza

1.41

 faudra

1.41

 disgruntled

1.39

玊

1.39



1.36



1.35

Activations Density 0.018%