INDEX

Explanations

asking or being asked

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

 something

1.08

Something

1.05

 något

0.99

 Something

0.98

something

0.97

 quelque

0.96

 somewhere

0.94

ாடு

0.91

ா

0.90

 возможно

0.89

POSITIVE LOGITS

نه

1.12

ductory

1.11

쪼

1.07

pośred

1.04

 stints

1.04

 Tregs

1.03

小說

1.01

toire

1.00

 sanitaria

0.98

标识

0.97

Activations Density 0.043%