INDEX

Explanations

indicators of personal or collective self-reflection and awareness

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

antal

-0.08

ntax

-0.07

cka

-0.07

atoon

-0.07

inski

-0.07

ledon

-0.07

alien

-0.06

ãĤ¿ãĥ³

-0.06

ç«ĭãģ¦

-0.06

illary

-0.06

POSITIVE LOGITS

str

0.33

(str

0.19

ve

0.17

str

0.17

=str

0.16

 stray

0.15

str

0.14

Str

0.14

.str

0.14

,str

0.14

Activations Density 0.710%