INDEX

Explanations

concepts related to decision-making and choice

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

eln

-0.07

EMPL

-0.07

(Mod

-0.07

 táº£

-0.06

byn

-0.06

eken

-0.06

wend

-0.06

Ø±Ø®

-0.06

atham

-0.06

etooth

-0.06

POSITIVE LOGITS

 matt

0.28

 matter

0.27

 matte

0.26

 mater

0.25

mat

0.25

 matters

0.24

matter

0.23

MAT

0.22

Âłm

0.22

mat

0.20

Activations Density 0.037%