INDEX

Explanations

discussions around moral and ethical questions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸Ģç§į

-0.08

ãĥ³ãĤº

-0.07

ibName

-0.07

ableObject

-0.07

IllegalAccessException

-0.07

caff

-0.06

ÅĻÃŃzenÃŃ

-0.06

Localized

-0.06

etooth

-0.06

Ã¡no

-0.06

POSITIVE LOGITS

kn

0.13

th

0.13

 pressing

0.13

 weight

0.12

 tough

0.11

vex

0.11

 burning

0.11

 nett

0.11

 fundamental

0.11

 perennial

0.10

Activations Density 0.059%