INDEX

Explanations

requires professional treatment

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

 rand

-0.09

POOL

-0.09

 confidence

-0.09

AGES

-0.09

.scalablytyped

-0.09

 surrogate

-0.09

))*(

-0.09

 pard

-0.09

 sore

-0.09

 profil

-0.08

POSITIVE LOGITS

 treatment

0.16

 Treatment

0.14

 stigma

0.13

 Recovery

0.13

 seeking

0.13

 recovery

0.12

 Seeking

0.12

Treatment

0.12

Seek

0.12

ialect

0.12

Activations Density 0.041%