INDEX

Explanations

there was/is/are

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

+}\

-0.93

=}

-0.89

？】

-0.87

+}$

-0.86

 INCOR

-0.85

 vertelt

-0.85

ható

-0.84

getApplication

-0.84

 herab

-0.84

ressão

-0.83

POSITIVE LOGITS

 such

0.84

“

0.83

 Another

0.82

 darunter

0.81

 Their

0.81

⑳

0.79

 plötzlich

0.78

 powinno

0.77

 warto

0.76

 Various

0.75

Activations Density 0.009%