INDEX

Explanations

Reform primary, movement, act

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

 oblivious

-0.96

btw

-0.95

 looming

-0.91

 あります

-0.89

CARACTERIST

-0.88

生ま

-0.87

ご連絡

-0.85

 taunt

-0.84

 گذاری

-0.83

哂

-0.83

POSITIVE LOGITS

ulated

1.55

ulation

1.38

ulate

1.34

ulations

1.22

ulates

1.09

ULATION

1.05

measures

1.02

ulat

0.99

graphies

0.98

ative

0.95

Activations Density 0.004%