INDEX

Explanations

model and layers definitions

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 والح

1.28

}^{

1.24

ડા

1.22

daad

1.16

 Accessed

1.13

мо

1.11

உ

1.07

 nhiên

1.05

вой

1.05

сти

0.98

POSITIVE LOGITS

rangian

1.45

 syndromes

1.43

nmea

1.36

€™

1.30

gtrsim

1.26

 nilpotent

1.25

1.24

на

1.22

 traitor

1.20

অ্যাপ

1.17

Activations Density 0.003%