INDEX

Explanations

software use, reproduction, distribution terms

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

/***

-0.98

melden

-0.96

Kuva

-0.93

getManager

-0.92

 something

-0.91

odyne

-0.91

 ſome

-0.90

 内衣

-0.90

Referanser

-0.88

Papier

-0.87

POSITIVE LOGITS

 whatsoever

1.18

へん

0.90

 besides

0.85

 jakie

0.83

 wyjątk

0.80

 obecnie

0.78

 trabajos

0.76

 khususnya

0.75

oraf

0.75

 onlar

0.74

Activations Density 0.105%