INDEX

Explanations

being followed by adjective

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

ણા

1.70

<0x80>

1.59

años

1.57

ول

1.54

ｒ

1.51

 आंच

1.51

لا

1.50

pt

1.49

 pouvant

1.46

 potholes

1.46

POSITIVE LOGITS

 able

2.33

ра

1.99

νες

1.97

 foremost

1.94

 hailed

1.92

рати

1.91

 связаны

1.89

 связано

1.89

 fined

1.86

 relieved

1.81

Activations Density 0.133%