INDEX

Explanations

references to violent confrontations or clashes

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/*++

-0.62

#+#

-0.61

proz

-0.61

 >=",

-0.58

elesai

-0.57

 mole

-0.56

essoal

-0.56

уза

-0.56

IsNotNull

-0.56

Ỗ

-0.54

POSITIVE LOGITS

 clash

3.41

 clashes

2.86

clash

2.73

 clashed

2.48

 Clash

2.38

Clash

2.11

 choque

0.87

 showdown

0.79

Mismatch

0.77

 mismatch

0.71

Activations Density 0.000%