INDEX

Explanations

prove, assumptions, outcomes

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

ړ

0.39

ربع

0.36

 لائ

0.35

றுத்த

0.35

rael

0.34

າມ

0.33

ۍ

0.33

Sense

0.32

ють

0.32

είται

0.32

POSITIVE LOGITS

 turns

1.30

 proved

1.22

 оказался

1.20

 оказалась

1.16

 prove

1.16

 proves

1.16

 proving

1.16

Turns

1.14

 оказались

1.14

 оказалось

1.13

Activations Density 0.096%