INDEX

Explanations

mental health professional

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

<unused72>

1.70

 niemals

1.48

 meines

1.45

കളുടെ

1.39

er

1.36

亠

1.34

θεν

1.34

 pernah

1.32

はこの

1.30

POSITIVE LOGITS

 Madness

1.40

 ambit

1.34

aikh

1.30

 Maest

1.30

ník

1.23

тна

1.23

1.21

 pronouns

1.19

铃

1.19

 crept

1.18

Activations Density 0.006%