INDEX

Explanations

signals in both time and frequency

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

 Plum

-0.10

 transmission

-0.10

bom

-0.09

 transc

-0.09

gri

-0.09

WithType

-0.09

 Calibration

-0.09

_BGR

-0.09

 dose

-0.09

wed

-0.08

POSITIVE LOGITS

 signal

0.16

 Lomb

0.14

 window

0.14

 Signal

0.14

 Window

0.14

(signal

0.13

 windows

0.13

 Welch

0.13

Window

0.13

window

0.13

Activations Density 0.049%