INDEX

Explanations

specific nouns followed by descriptive phrasing

This neuron flags the main subject nouns (like car, wheels, track, hill, matches, championship) that denote the central objects in math and physics problem statements.

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

 mascarilla

-1.23

ὓ

-1.23

heren

-1.23

 sièges

-1.20

 erreurs

-1.17

kyrie

-1.16

 véritables

-1.15

 améli

-1.15

 itinéraires

-1.13

 apporter

-1.11

POSITIVE LOGITS

 this

2.28

 with

1.90

 these

1.68

at

1.48

if

1.39

 each

1.34

for

1.28

 should

1.23

 tersebut

1.20

 using

1.19

Activations Density 0.054%