INDEX

Explanations

linguistics, philosophy, social science

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å

-0.08

 diabetes

-0.08

 toko

-0.08

Lemma

-0.07

.stroke

-0.07

 osteoporosis

-0.07

 obstacle

-0.07

 coté

-0.07

 passant

-0.07

 consectetur

-0.07

POSITIVE LOGITS

 interplay

0.10

不断

0.09

 tapes

0.09

 amalg

0.09

 constantly

0.08

"][

0.08

 tapestry

0.08

�

0.08

 weave

0.08

 patterned

0.07

Activations Density 0.034%