INDEX

Explanations

oval shapes, pairs of items

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

 xạ

1.05

 albo

0.95

 Roshelle

0.90

鴟

0.89

֒

0.86

 необходимость

0.86

 исключительно

0.85

揄

0.83

soever

0.82

حافظ

0.82

POSITIVE LOGITS

ten

1.40

AN

1.16

an

1.02

ting

1.01

1.00

tene

0.98

ti

0.97

TERS

0.97

ta

0.96

 snapped

0.96

Activations Density 0.000%