INDEX
Explanations
proper nouns related to real individuals named "Ron"
mentions of the name "Ron."
New Auto-Interp
Negative Logits
uated
-0.63
LER
-0.61
rigging
-0.61
Pixie
-0.60
EMP
-0.59
subord
-0.58
Corpus
-0.58
LOAD
-0.57
magnitude
-0.56
ready
-0.56
POSITIVE LOGITS
aldo
1.10
ald
1.07
nie
1.06
ny
0.99
Swanson
0.95
nen
0.94
Weasley
0.91
stadt
0.90
igans
0.85
igan
0.84
Activations Density 0.017%