INDEX

Explanations

organizations

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Principal

-0.93

 principal

-0.93

principal

-0.85

Principal

-0.78

co

-0.77

bat

-0.69

 PRINCIPAL

-0.65

mm

-0.63

MM

-0.60

 fashion

-0.57

POSITIVE LOGITS

 itſelf

0.88

httphttps

0.78

 pleaſure

0.77

 themſelves

0.76

 Phry

0.75

 vectorstock

0.74

 Reſ

0.74

Efq

0.74

 neceff

0.73

 houſe

0.72

Activations Density 1.102%