INDEX

Explanations

common things people say

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

2.25

 thermique

1.90

ciano

1.81

诵

1.75

 lässt

1.71

 réalisée

1.70

cipher

1.66

 verwend

1.65

endet

1.65

संह

1.62

POSITIVE LOGITS

م

2.09

ти

1.86

्टी

1.77

ות

1.74

сть

1.67

вання

1.67

м

1.66

야

1.62

Պ

1.62

Piv

1.60

Activations Density 0.067%