INDEX

Explanations

time, units, and formulas

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ׁ

1.57

 disponer

1.34

 hữu

1.31

ての

1.31

sequent

1.27

шня

1.25

 Bedürfnisse

1.24

rarse

1.24

 capitalise

1.24

涕

1.23

POSITIVE LOGITS

モ

1.59

受伤

1.58

混

1.53

装修

1.48

做了

1.46

ع

1.46

র

1.45

這

1.44

 جميل

1.42

 تع

1.42

Activations Density 0.000%