INDEX

Explanations

coalescing, conjuring, investigating, exploring

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

čnosti

0.78

ᄆ

0.78

ணர்வு

0.73

czną

0.72

iski

0.70

тности

0.70

czki

0.69

悱

0.69

льности

0.68

 Encoder

0.67

POSITIVE LOGITS

uating

1.24

ulating

1.18

itating

1.17

uring

1.13

ating

1.12

igating

1.10

ulated

1.06

ored

1.03

inating

1.03

itated

1.03

Activations Density 0.539%