INDEX

Explanations

attack on, attacked, attacking

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

ت

2.62

عة

2.49

ン

2.48

که

2.40

말로

2.39

도

2.38

睬

2.34

രുവനന്തപു

2.31

an

2.24

 bustle

2.20

POSITIVE LOGITS

ffiche

2.49

av

2.47

 сон

2.39

 remoto

2.36

 lire

2.24

 verwend

2.24

 destinés

2.23

meas

2.19

これも

2.19

로

2.18

Activations Density 0.042%