INDEX

Explanations

describing transformation and states

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

𝑦

3.60

an

3.13

ра

2.56

𝑘

2.44

anel

2.42

𝑐

2.37

 estés

2.34

𝑣

2.32

𝑥

2.28

оп

2.26

POSITIVE LOGITS

м

4.01

ع

3.08

べく

2.81

 increasingly

2.66

ின்

2.65

 embroiled

2.64

ต้อง

2.60

 deci

2.58

 testament

2.55

ди

2.50

Activations Density 0.058%