INDEX

Explanations

Erin or Fearing

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

 they

-1.13

 mendengar

-1.05

if

-1.05

you

-0.97

 their

-0.96

 cocina

-0.96

 capot

-0.95

 meminta

-0.94

mış

-0.94

ண்டும்

-0.92

POSITIVE LOGITS

Instead

1.08

 instead

1.05

 באמצ

1.00

 remaining

0.98

悻

0.93

 específicas

0.91

nej

0.90

 לאחר

0.89

HER

0.87

Seven

0.86

Activations Density 0.000%