INDEX
Explanations
metaphorical comparisons involving objects and relationships
New Auto-Interp
Negative Logits
assin
-0.07
pregn
-0.07
orde
-0.06
>>)
-0.06
(*)(
-0.06
Orient
-0.06
empre
-0.06
Plan
-0.06
uranus
-0.06
амеÑĤ
-0.06
POSITIVE LOGITS
example
0.09
above
0.09
ä¾ĭ
0.08
those
0.08
Above
0.07
Above
0.07
hypothetical
0.07
analogy
0.07
Example
0.07
.example
0.07
Activations Density 0.020%