INDEX

Explanations

informal text evaluations and non-english

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

</h2>

0.31

 memoranda

0.28

»:

0.27

を用いた

0.27

0.26

 REACTORS

0.25

 radionuclides

0.25

URS

0.24

REACTOR

0.24

ЛИ

0.24

POSITIVE LOGITS

 crappy

0.35

 nifty

0.32

 ammo

0.32

 really

0.31

 kinda

0.31

 udah

0.31

really

0.30

ahh

0.30

 अलावा

0.30

Activations Density 0.020%