INDEX
Explanations
references to the historical figure Richard Nixon
references to Richard Nixon and related events
New Auto-Interp
Negative Logits
================================================================
-0.77
tered
-0.76
acters
-0.75
FORM
-0.74
medium
-0.72
Flavoring
-0.69
ivities
-0.68
umen
-0.67
WHERE
-0.66
topic
-0.66
POSITIVE LOGITS
shire
0.95
Nixon
0.87
Jr
0.68
Watergate
0.66
oxide
0.65
Jong
0.65
iere
0.65
Sut
0.64
eters
0.62
enthal
0.62
Activations Density 0.012%