INDEX

Explanations

nuclear energy, power, and weapons

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

ной

0.76

ного

0.73

es

0.72

ку

0.71

al

0.70

0.64

𝗿

0.61

льного

0.60

 habrá

0.58

POSITIVE LOGITS

 Nuclear

0.76

 nuclear

0.68

Nuclear

0.64

 IAEA

0.57

 Atomic

0.57

 isotopes

0.56

by

0.55

 fission

0.54

 NUCLEAR

0.53

 egen

0.52

Activations Density 0.008%