INDEX

Explanations

software licensed and made available under

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

膜

-0.77

Mav

-0.71

 Savannah

-0.71

ordion

-0.68

 ataques

-0.68

 ramp

-0.68

PLATE

-0.67

 buds

-0.67

Bud

-0.67

 cavity

-0.67

POSITIVE LOGITS

 lampa

0.68

 alfabe

0.65

 oversized

0.65

邈

0.65

 hommage

0.64

 supr

0.63

PosY

0.63

dura

0.63

検

0.62

cogn

0.61

Activations Density 0.080%