INDEX

Explanations

parenthesized numbers and letters

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

০০

1.95

ból

1.84

 Při

1.71

자

1.69

ução

1.68

 टूटा

1.58

ární

1.58

 být

1.57

iż

1.57

ción

1.56

POSITIVE LOGITS

ف

1.77

 careg

1.60

с

1.55

ർ

1.50

astype

1.48

 politie

1.48

 flavor

1.47

箐

1.45

iet

1.43

์

1.41

Activations Density 0.030%