INDEX

Explanations

that followed by various words

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

्रिया

1.27

 durum

1.27

𝘇

1.27

ется

1.25

 cere

1.23

 زمان

1.21

𝘀

1.21

cui

1.20

за

1.15

 Público

1.15

POSITIVE LOGITS

ARE

1.94

ıyla

1.82

ো

1.77

ів

1.68

야

1.68

 поводу

1.57

 лишь

1.55

ou

1.54

OOOO

1.54

ى

1.53

Activations Density 0.043%