INDEX

Explanations

one event causes

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

enant

-0.10

Lav

-0.10

ancellationToken

-0.09

 jadx

-0.09

 /*č\n

-0.09

RuleContext

-0.09

duino

-0.09

aterno

-0.09

âĶģ

-0.08

indow

-0.08

POSITIVE LOGITS

 events

0.17

 event

0.16

 cause

0.16

 Cause

0.15

cause

0.14

Events

0.14

äºĭä»¶

0.13

 Events

0.13

ca

0.13

event

0.13

Activations Density 0.043%