INDEX

Explanations

cl followed by 'uck', 'ods', 'unky', 'itor', 'umping', 'itoral', 'op', 'oying', 'ojure'

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

1.55

or

1.35

ك

1.31

ים

1.27

ς

1.19

in

1.12

on

1.10

1.07

ка

1.05

the

1.05

POSITIVE LOGITS

اً

0.87

adayo

0.77

epers

0.77

 влияние

0.75

،

0.75

 khăn

0.74

itabbam

0.74

ensión

0.73

 Geißler

0.73

 När

0.72

Activations Density 0.002%