INDEX

Explanations

verbs describing actions or functions

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

只

0.44

 μόνο

0.39

بع

0.38

 только

0.38

 occurrence

0.38

出现的

0.37

 vừa

0.36

 רק

0.36

เกิดขึ้น

0.36

只有一个

0.35

POSITIVE LOGITS

 rispetto

0.44

 mengenal

0.43

cono

0.42

cfm

0.41

怵

0.41

 esattamente

0.41

haram

0.40

andha

0.39

はや

0.38

 exactement

0.38

Activations Density 0.074%