INDEX

Explanations

mathematical formulas and symbols

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

े

2.30

 dimensionless

1.91

ль

1.88

вые

1.86

 praw

1.84

ःख

1.82

জন

1.81

 relato

1.76

ه

1.76

های

1.74

POSITIVE LOGITS

er

2.90

ر

2.35

্ড

2.31

<0x80>

2.30

prav

2.30

inės

2.22

ك

2.18

 знако

2.16

lisi

2.15

2.12

Activations Density 0.045%