INDEX

Explanations

Wil

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

ReusableCell

-0.60

 Silly

-0.58

Silly

-0.56

inaldi

-0.54

 love

-0.53

Hochspringen

-0.51

silly

-0.51

🧤

-0.51

ModelAdmin

-0.51

 Milne

-0.50

POSITIVE LOGITS

 بيها

0.59

Personensuche

0.49

 consegu

0.47

openqa

0.46

bpy

0.45

 chi̍t

0.45

WaitGroup

0.44

SBATCH

0.43

ఔ

0.43

toch

0.42

Activations Density 0.001%