INDEX

Explanations

explaining how things work

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

ре

2.18

ро

1.91

е

1.86

ẹn

1.84

ل

1.83

ایی

1.82

os

1.81

েন

1.77

с

1.74

и

1.72

POSITIVE LOGITS

目の

2.25

sion

2.24

পেক্ষ

2.19

denly

2.18

llium

2.15

 rağmen

2.13

 Omphalodes

2.11

 phosphorylated

2.07

日本では

2.07

xCoordinate

2.02

Activations Density 0.153%