INDEX

Explanations

blowing up, blowing out, blowing snow

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

.”

-2.56

at

-2.34

ar

-2.33

-2.30

-2.17

 have

-2.08

of

-1.97

ஂ

-1.95

On

-1.93

POSITIVE LOGITS

 grün

2.02

1.95

鬭

1.92

 braços

1.91

 vijf

1.90

warnai

1.90

 gelb

1.87

zeppelin

1.85

</strong>

1.84

 dunkel

1.81

Activations Density 0.010%