INDEX

Explanations

Okay, let's break down

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



1.73

$\

1.63

⎡

1.61

″

1.57

$.;

1.57

му

1.54

tuple

1.53

te

1.47

 tige

1.45

ам

1.44

POSITIVE LOGITS

श

2.05

 Begriffe

1.73

 allez

1.73

 pikir

1.72

Здравствуйте

1.72

जुर्ग

1.71

 commute

1.66

ie

1.66

ધ

1.65

უბ

1.64

Activations Density 0.138%