INDEX

Explanations

No Explanations Found

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

 cổng

1.04

 каран

1.03

 sideways

1.02

탱

0.99

 alcal

0.98

 springtime

0.98

 sals

0.97

 Avenue

0.96

봉

0.95

ဏ်

0.95

POSITIVE LOGITS

uncertain

1.40

 gaps

1.30

 imprecise

1.29

research

1.28

Confusion

1.27

 unclear

1.27

scientific

1.27

bibliography

1.25

 confusion

1.22

confusion

1.21

Activations Density 0.401%

No Known Activations