INDEX

Explanations

literal vs figurative

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

bla

0.40

شمند

0.39

 clade

0.38

 সীমান্তবর্তী

0.36

するなど

0.35

is

0.35

 gerade

0.35

വ

0.34

idious

0.34

م

0.34

POSITIVE LOGITS

 proverbial

0.54

 literalmente

0.52

 figuratively

0.50

 figurative

0.45

 metaphorical

0.45

 proverb

0.43

 metaphor

0.40

 Literally

0.39

 konular

0.37

literal

0.36

Activations Density 0.015%