INDEX

Explanations

quantified measurements and scores

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

駐車場

1.09

nur

1.09

Nib

1.04

いに

1.02

 mög

1.01

據

1.00

래

1.00

 QUAD

0.99

ligt

0.98

 Syri

0.98

POSITIVE LOGITS

")))

1.36

!"));

1.32

JECTION

1.30

ENCED

1.30

匮

1.29

\"",

1.25

opium

1.21

/[\

1.19

anomaly

1.19

encher

1.19

Activations Density 0.107%