INDEX

Explanations

vulnerable and susceptible

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

межу

0.66

মানের

0.65

 satisfactory

0.64



0.62

ட்டும்

0.62

{(-

0.61

itatively

0.60

晌

0.59

ങ്ങനെ

0.59

满足

0.58

POSITIVE LOGITS

 vulnerable

3.08

 susceptible

3.06

 prone

2.94

 vulnerability

2.93

 susceptibility

2.88

 risk

2.82

 Vulner

2.66

Risk

2.56

prone

2.52

 Risk

2.51

Activations Density 1.045%