INDEX

Explanations

subject pronoun followed by 'd or had

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

myX

0.54

 моих

0.53

 helium

0.45

 Helium

0.44

 എന്റെ

0.43

当量

0.43

芡

0.43

 monatomic

0.41

 나의

0.41

myTransform

0.41

POSITIVE LOGITS

 suspect

0.71

 suspected

0.66

 suspects

0.64

 swore

0.63

 vaguely

0.62

 swear

0.60

 swears

0.59

 sospe

0.57

 hadn

0.56

 подозре

0.56

Activations Density 0.029%