INDEX

Explanations

machine learning concepts

This neuron activates on tokens belonging to the structural elements of academic papers—section headers, reference markers, bibliography fields, author names, and related metadata.

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

("/:

-0.76

ється

-0.71

 unset

-0.69

 stun

-0.69

議会

-0.68

 Simulation

-0.68

انه

-0.67

ђе

-0.67

"=>$

-0.67

 stressors

-0.67

POSITIVE LOGITS

 learning

1.38

learning

1.23

Learning

1.13

 aprendizaje

1.08

 Learning

1.08

LEARNING

1.02

 Machine

1.00

 LEARNING

0.97

 machine

0.95

Machine

0.93

Activations Density 0.043%