INDEX

Explanations

random comments, observations, thoughts

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

ου

1.30

್ರ

1.27

 Tahoma

1.25

ítás

1.22

″

1.15

ერის

1.13

 மூலம்

1.12

鸯

1.11

fach

1.09

centage

1.09

POSITIVE LOGITS

1.20

1.14

ми

1.13

in

1.09

bies

1.08

 nucleotides

1.04

 वेळी

1.04

ेल

1.03

ع

1.02

ィ

1.02

Activations Density 0.005%