INDEX

Explanations

audio and sound-related contexts

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

悱

1.57

ziert

1.55

 aussitôt

1.52

 trình

1.49

 hypotheses

1.49

 длиной

1.49

 inguinal

1.48

تي

1.46

২

1.45

 miracles

1.44

POSITIVE LOGITS

<bos>

1.64

körper

1.58

bite

1.49

argent

1.43

pepper

1.41

*((

1.40

stereo

1.40

 behold

1.39

emph

1.39

Baseline

1.38

Activations Density 0.045%