INDEX

Explanations

names and surnames

This neuron detects author surnames (capitalized last names) in paper metadata (e.g. in author lists).

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

to

-2.38

as

-1.89

].

-1.66

]}$

-1.59

,”

-1.52

”.

-1.48

.”

-1.45

 auriculares

-1.39

などを

-1.39

 temi

-1.38

POSITIVE LOGITS

مزید

1.52

źdz

1.44

 préc

1.43

 soulign

1.42

СКА

1.42

 soñar

1.41

 muhimu

1.38

如此

1.36

 rencont

1.35

Zubereitung

1.35

Activations Density 0.064%