INDEX

Explanations

punishing mistakes, rewarding exploration, take damage

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

chehen

0.72

 provenance

0.72

 वर्चुअल

0.71

Provenance

0.71

{$

0.71



0.70

 rzeczyw

0.69

 genealog

0.69

受信

0.69

 미술

0.69

POSITIVE LOGITS

DPS

1.16

 teammates

1.11

 spam

1.07

 harass

1.05

 combo

1.05

 damage

1.05

 combos

1.04

DPS

1.04

 heal

1.01

 kill

1.00

Activations Density 0.388%