INDEX

Explanations

comfort and comfort-related words

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/@

-0.08

ECT

-0.08

atts

-0.08

erva

-0.08

inel

-0.08

-striped

-0.08

declar

-0.08

 Flags

-0.08

artz

-0.08

pect

-0.08

POSITIVE LOGITS

 comfortable

0.15

 Comfort

0.14

 uncomfortable

0.14

 comfort

0.13

 discomfort

0.13

Comfort

0.12

comfort

0.11

 comforts

0.11

 familiarity

0.11

 confort

0.11

Activations Density 0.124%