INDEX

Explanations

even further/better/though

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

leri

1.36

 inflict

1.34

ð

1.28

 lẽ

1.27

1.26

\}$

1.25

siniz

1.25

ce

1.24

 đều

1.24

 entail

1.24

POSITIVE LOGITS

verständlich

1.65

handed

1.48

एस

1.41

 불구하고

1.37

可以说是

1.36

らった

1.35

handedly

1.35

होस्

1.34

いた

1.33

 불구

1.33

Activations Density 0.004%