INDEX

Explanations

Kit

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ivelany

-0.87

 AssemblyTitle

-0.84

reportWebVitals

-0.77

 referenties

-0.73

 pleaſure

-0.72

 kasarigan

-0.70

EndProject

-0.70

يميديا

-0.70

رشف

-0.69

Identyfik

-0.69

POSITIVE LOGITS

nlm

0.55

0.51

тинга

0.46

0.44

0.43

oli

0.41

LU

0.41

邑

0.40

<b>

0.39

nstein

0.38

Activations Density 0.380%