INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elif

0.80

一共

0.77

즉

0.77

はもちろん

0.76

なら

0.76

artha

0.76

ならば

0.75

的前提

0.74

>=</

0.74

 इत्या

0.72

POSITIVE LOGITS

 some

4.52

 بعض

4.36

some

4.35

Some

4.22

 algunos

4.08

 Some

4.07

 certains

3.99

 некоторых

3.97

 alcuni

3.91

بعض

3.88

Activations Density 2.164%

No Known Activations