INDEX

Explanations

doubled in size or value

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 परसेंटेज

0.44

 frequentemente

0.40

罷

0.37

こともある

0.37

';",

0.37

nCurr

0.36

逡

0.35

Percentages

0.34

逑

0.34

計算

0.34

POSITIVE LOGITS

 doubled

1.39

 doubling

1.33

 doubles

1.28

 double

1.12

 Doubles

1.01

Dou

1.00

Dou

1.00

dou

0.96

 Double

0.96

double

0.95

Activations Density 0.001%