INDEX
Explanations
dates in the format "Month Dayth" and locations starting with "between"
New Auto-Interp
Negative Logits
faced
-0.74
needed
-0.70
rav
-0.67
resy
-0.67
cn
-0.66
hops
-0.66
itivity
-0.66
seek
-0.64
rite
-0.64
conflic
-0.64
POSITIVE LOGITS
afar
1.28
inception
1.14
whence
1.04
1901
0.97
conception
0.96
thence
0.94
1951
0.94
1955
0.91
1961
0.90
1957
0.89
Activations Density 0.113%