INDEX

Explanations

model theories and examples

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

 Hain

1.22

 Vort

1.22

Xan

1.19

Hsu

1.18

шым

1.17

Qu

1.17

:$

1.16

 Hutchinson

1.15

 Harn

1.15

}:$

1.15

POSITIVE LOGITS

 Model

1.27

 model

1.27

Model

1.23

model

1.11

 models

0.95

 Models

0.94

模型

0.91

 modelo

0.91

 modèle

0.88

 MODEL

0.88

Activations Density 0.109%