INDEX

Explanations

play followed by a game or activity

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

1.56

не

1.54

ди

1.52

ة

1.52

speople

1.48

 plunging

1.41

ó

1.41

si

1.36

თ

1.35

 ascertain

1.34

POSITIVE LOGITS

ందుకు

1.73

ر

1.72

isasi

1.66

ிர்

1.65

ент

1.61

 ситуацию

1.59

ischer

1.58

ασία

1.58

 Deshalb

1.55

الة

1.54

Activations Density 0.065%