INDEX
Explanations
references to a person named Murphy
mentions of the name "Murphy."
New Auto-Interp
Negative Logits
arian
-0.90
omething
-0.86
iary
-0.83
owed
-0.82
agy
-0.80
onent
-0.80
arin
-0.79
edly
-0.79
ivist
-0.78
aq
-0.77
POSITIVE LOGITS
ufact
0.75
Bom
0.70
QC
0.69
Train
0.63
acht
0.63
hler
0.62
Hath
0.62
Barr
0.62
Deal
0.59
Dent
0.59
Activations Density 0.098%