INDEX

Explanations

intelligence

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Intellectual

-1.27

intelligent

-1.20

 intelligent

-1.19

intellectual

-1.18

intelligence

-1.13

 intellectual

-1.12

 intellectually

-1.12

 intelligence

-1.09

 Intellectual

-1.08

 intelligente

-1.07

POSITIVE LOGITS

ity

0.96

ness

0.70

️

0.64

ized

0.60

ism

0.60

ization

0.57

ly

0.56

ITY

0.56

ry

0.54

ising

0.53

Activations Density 0.300%