INDEX

Explanations

mathematical expressions and formulas

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

 auditory

0.91

=',')

0.85

ografie

0.83

 charismatic

0.81

}=\{

0.80

 salaried

0.80

 nicknamed

0.80

 Tuesdays

0.80

 poeta

0.78

 entrenched

0.78

POSITIVE LOGITS

((

1.82

((

1.81

[(

1.75

[(

1.69

(((

1.51

frac

1.46

(((

1.44

([(

1.40

((-

1.22

 √(

1.22

Activations Density 0.575%