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

 travail

1.51

 steering

1.33

 agony

1.31

 indignation

1.30

м

1.25

 Tätigkeit

1.23

`./

1.21

 hígado

1.20

 adulter

1.19

 sourdough

1.19

POSITIVE LOGITS

larıyla

1.08

ки

1.08

 zhī

1.06

elems

1.06

א

1.04

Granted

1.02

months

0.99

Sail

0.98

arıyla

0.97

Hour

0.96

Activations Density 0.000%

No Known Activations

This feature has no known activations.