INDEX

Explanations

conversational examples

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

Eri

1.05

тинен

0.99

тиву

0.96

ți

0.94

rir

0.92

љ

0.91

ris

0.91

ional

0.90

iture

0.89

POSITIVE LOGITS

aidl

1.35

abetic

1.34

']:

1.30

otrop

1.28

 getType

1.25

 reak

1.23

 '}';

1.23

物の

1.22

helium

1.20

%]

1.20

Activations Density 0.002%