INDEX

Explanations

conjunctions, negation, verbs

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

1.76

،

1.66

፣

1.34

,$$

1.30

，

1.24

–

1.23

、

1.23

(),

1.15

,\\

1.10

.,

1.06

POSITIVE LOGITS

 cannot

0.91

cannot

0.89

 valamint

0.88

 tetapi

0.86

 mutta

0.85

etc

0.83

 પરંતુ

0.81

but

0.80

 लेकिन

0.80

 koska

0.79

Activations Density 0.073%