INDEX
Explanations
refrigerator or fridge appliance
New Auto-Interp
Negative Logits
refrigerators
0.69
Refriger
0.69
refrigerated
0.68
refrigeration
0.67
appliances
0.60
Appliances
0.59
refriger
0.58
appliance
0.58
fridge
0.55
冷蔵
0.55
POSITIVE LOGITS
smuggled
0.45
తమి
0.45
playbook
0.43
magnetometer
0.42
coulomb
0.42
brainstorm
0.42
蓽
0.41
Yokohama
0.40
idiosync
0.40
kaleidos
0.40
Activations Density 0.002%