INDEX

Explanations

confidential document

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

 Surveillance

0.55

 surveillance

0.52

spy

0.49

监控

0.49

 spies

0.49

 probes

0.48

 spying

0.48

 risques

0.47

Spy

0.46

Spy

0.46

POSITIVE LOGITS

CIA

0.66

CIA

0.66

 đau

0.60

 wounding

0.59

 overthrow

0.57

的处理

0.57

cia

0.57

 distribusi

0.56

処理

0.56

 contradict

0.54

Activations Density 0.066%