INDEX

Explanations

makes it clearer, harder, different, easier

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

ads

1.23

м

1.23

おります

1.21

adding

1.20

 Farrell

1.19

ções

1.15

हमारी

1.14

barrels

1.13

ops

1.13

rods

1.13

POSITIVE LOGITS

1.18

kennung

1.16

 وبين

1.14

leukin

1.09

krb

1.05

)!=

0.98

 أيضاً

0.98

kina

0.98

^{*}}\

0.96

 Еще

0.93

Activations Density 0.000%