INDEX

Explanations

action verbs ending in -ing

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

鹩

-1.62

墊

-1.59

すっ

-1.52

albeit

-1.47

 occuper

-1.45

の紹介

-1.44

ぽん

-1.42

 nettoy

-1.41

を探す

-1.41

鶫

-1.39

POSITIVE LOGITS

for

2.13

an

1.95

and

1.79

at

1.67

 under

1.63

in

1.62

 using

1.59

 four

1.59

or

1.56

on

1.53

Activations Density 0.160%