INDEX

Explanations

sentencing hearings and Irish state lawsuits

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istrat

-0.11

 indict

-0.11

Tud

-0.10

 indictment

-0.09

 Trent

-0.09

 Campos

-0.09

arters

-0.09

Tib

-0.08

.ar

-0.08

idden

-0.08

POSITIVE LOGITS

lib

0.20

Lib

0.12

 damages

0.12

 Silk

0.12

 defamation

0.12

 retr

0.12

 Pais

0.11

 High

0.11

 contempt

0.11

QC

0.11

Activations Density 0.035%