INDEX

Explanations

jokes that start with why don't scientists trust

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

er

0.85

hindi

0.78

on

0.78

ताई

0.78

ка

0.77

குறித்து

0.75

व्ह

0.73

ooo

0.71

person

0.71

POSITIVE LOGITS

 been

1.14

 gotta

1.12

 Been

1.10

 BEEN

1.10

 gonna

1.08

行く

1.07

Got

1.02

 goin

1.01

got

1.00

 going

0.99

Activations Density 0.017%