INDEX

Explanations

deviate from norms or expectations

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

ر

3.06

`${

3.05

 damn

2.95

 собой

2.76

ലീസ്

2.73

替え

2.69

erche

2.65

鍖

2.62

 lingk

2.57

ᴏ

2.55

POSITIVE LOGITS

此之外

3.04

 улицы

2.99

ی

2.91

ባድ

2.77

𝙩

2.71

्टर

2.68

trading

2.59

нең

2.58

 Eshelby

2.51

ни

2.50

Activations Density 0.041%