INDEX

Explanations

on [verb ending in -ing]

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

 وعلى

3.86

 behalf

2.50

 horseback

2.13

िक्रमा

1.88

 základě

1.87

 úrov

1.84

 podstawie

1.81

 steroids

1.80

1.75

്

1.74

POSITIVE LOGITS

ت

2.44

्स

2.09

2.08

س

2.05

ו

2.02

től

1.95

ek

1.91

ture

1.88

ע

1.88

1.87

Activations Density 0.183%