INDEX

Explanations

concepts related to identity and belonging

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

awy

-0.07

onda

-0.07

ohana

-0.06

ewan

-0.06

uky

-0.06

ãģ°ãģĭãĤĬ

-0.06

redo

-0.06

uesta

-0.06

owed

-0.06

POSITIVE LOGITS

 alright

0.25

 indeed

0.23

inde

0.17

 Indeed

0.14

Indeed

0.13

 certainly

0.12

 Alright

0.11

OK

0.11

OK

0.10

 totiÅ¾

0.10

Activations Density 0.068%