INDEX

Explanations

policy automatically

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

‌,

1.50

‌

1.45

ríklad

1.44

‌

1.40

<unused2169>

1.39

<0xE2>

1.38

 टेलीविजन

1.38

 बृहस्पतिवार

1.35

 ব্যাকটেরিয়া

1.31

<unused2197>

1.29

POSITIVE LOGITS

ppl

3.15

 kinda

2.94

đc

2.79

 IMHO

2.76

 crappy

2.58

ってる

2.55

yg

2.52

 VERY

2.52

 shitty

2.47

(?)

2.47

Activations Density 1.848%