INDEX

Explanations

actions of natural forces

The neuron flags present-tense words naming natural phenomena in action—especially “blowing” and “shining.”

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

TextWatcher

-1.76

적으로

-1.56

鹇

-1.48

руется

-1.45

それを

-1.42

見学

-1.41

تين

-1.41

讴

-1.40

 using

-1.39

匐

-1.37

POSITIVE LOGITS

in

1.80

increased

1.65

 conocen

1.50

 joyful

1.49

 blatant

1.48

1.46

 peculiar

1.45

っていない

1.43

 insanely

1.41

wholesale

1.41

Activations Density 0.039%