INDEX

Explanations

University of

The neuron flags tokens that are part of formal organization or institution names—especially “University of …” style phrases.

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

our

-1.46

on

-1.43

 probably

-1.34

。

-1.32

 likely

-1.31

.”

-1.30

two

-1.28

-1.27

 certainly

-1.25

mycompany

-1.24

POSITIVE LOGITS

 mencoba

1.35

驮

1.30

はじめ

1.28

 florales

1.28

 入り

1.27

 pouvoir

1.27

Ѿ

1.27

 berbicara

1.26

出来ない

1.22

 voulons

1.22

Activations Density 0.139%