INDEX

Explanations

abbreviations like Nb, sb, ab

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

ן

2.11

dır

2.06

ל

2.03

1.90

 μεγάλη

1.88

 Curves

1.84

वर

1.81

기

1.81

larımız

1.77

রা

1.75

POSITIVE LOGITS

м

2.55

Луч

1.97

 bodied

1.95

 aspett

1.91

 কিন্ত

1.90

 annat

1.87

 prosent

1.86

夠

1.85

কিন্ত

1.79

essä

1.79

Activations Density 0.466%