INDEX

Explanations

one after certain verbs/prepositions

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

ഘടന

0.78

<unused615>

0.78

 vutta

0.77

વવા

0.77

 වශයෙන්

0.74

тпу

0.73

 സമ്പ

0.72

codewords

0.71

 tutta

0.69

什么样的

0.69

POSITIVE LOGITS

one

4.56

 یکی

4.07

one

3.41

 один

3.30

 одной

3.25

 אחד

3.23

 одним

3.18

 salah

3.17

 одном

3.14

 أحد

3.13

Activations Density 0.342%