INDEX

Explanations

enter, outside, find, traveling

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

lero

-0.10

 Abrams

-0.10

lane

-0.10

 Apostle

-0.09

 ï¼ľ

-0.09

 evac

-0.08

_depart

-0.08

uddenly

-0.08

.pivot

-0.08

POSITIVE LOGITS

 onto

0.20

onto

0.19

 into

0.15

into

0.15

 INTO

0.14

_into

0.13

 headed

0.12

.into

0.12

Into

0.11

Ont

0.11

Activations Density 0.051%