INDEX

Explanations

words containing "horn"

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

ControlButton

0.42

rita

0.41

ritus

0.40

CONTROL

0.39

anooga

0.38

وني

0.38

plify

0.38

Mount

0.37

antos

0.37

icillium

0.37

POSITIVE LOGITS

 sizz

0.38

pys

0.37

 Clause

0.36

 Mendel

0.36

Pip

0.36

aset

0.36

 benz

0.36

 Blume

0.36

 eigentlich

0.35

ear

0.35

Activations Density 0.002%