INDEX
Explanations
references to historical scientists and their contributions
New Auto-Interp
Negative Logits
bjerg
-0.15
odash
-0.14
antino
-0.14
ÄŁer
-0.13
μά
-0.13
iren
-0.13
ÑĸйÑģ
-0.13
flag
-0.13
wa
-0.13
staw
-0.13
POSITIVE LOGITS
invent
0.62
Invent
0.59
inventor
0.55
invention
0.52
inventions
0.49
scientist
0.38
invented
0.36
scientists
0.35
scientific
0.34
Scientist
0.32
Activations Density 0.195%