INDEX

Explanations

implement or implemented

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

ள்ளது

1.98

ী

1.88

ように

1.80

서

1.80

сть

1.76

夠

1.76

Comunic

1.67

นี้

1.65

unction

1.64

punkt

1.64

POSITIVE LOGITS

ښت

1.65

что

1.55

ത്തിക

1.52

⿱

1.43

ى

1.43

clusive

1.41

 стоимо

1.41

फारिश

1.41

थरूम

1.41

 للغاية

1.41

Activations Density 0.016%