INDEX

Explanations

no X is like Y

This neuron detects expressions stating that “no two” (or “not two”) things are the same or alike—that is, negated statements of identicality.

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

 FUTURE

-1.00

 plutôt

-0.96

 abstrak

-0.95

 gari

-0.94

rather

-0.93

🪲

-0.91

 rather

-0.90

 klien

-0.90

IPAC

-0.89

IDER

-0.89

POSITIVE LOGITS

any

1.48

 anywhere

1.32

 anyone

1.18

 same

1.07

 anything

1.02

nor

0.96

 anymore

0.94

 anybody

0.90

ANY

0.87

 Always

0.86

Activations Density 0.043%