INDEX

Explanations

terms related to healthcare and medical professions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mr

-0.08

 actor

-0.07

 boyfriend

-0.07

 Actors

-0.07

 Actor

-0.07

 Father

-0.07

Uvs

-0.07

 grandfather

-0.07

 Husband

-0.07

 father

-0.07

POSITIVE LOGITS

atrice

0.13

stress

0.11

rice

0.11

atrix

0.10

adora

0.10

ress

0.09

ATRIX

0.09

resse

0.09

adress

0.09

cess

0.09

Activations Density 0.009%