INDEX

Explanations

No Explanations Found

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

 चाहें

2.11

𝘤

2.08

 kinks

1.91

 hump

1.88

ació

1.85

 Paco

1.82

 Unite

1.81

 Varan

1.80

ліка

1.80

 clairement

1.79

POSITIVE LOGITS

 Conversations

2.27

 Corner

2.00

 وعلى

1.95

芎

1.91

 Cosa

1.88

 Callback

1.85

 Canine

1.80

 Couleur

1.74

woman

1.73

 Conjecture

1.73

Activations Density 4.621%

No Known Activations