INDEX

Explanations

actions or negative states

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

깔

0.40

 γνωσ

0.38

translational

0.37

깔

0.37

能够

0.37

相比

0.36

Able

0.36

嫻

0.36

publicKey

0.36

 idéal

0.35

POSITIVE LOGITS

 injured

1.77

 damaged

1.65

 afflicted

1.63

 wounded

1.55

 பாதிக்கப்பட்ட

1.51

 distressed

1.46

 oppressed

1.46

 ravaged

1.46

 troubled

1.45

 stricken

1.44

Activations Density 0.036%