INDEX
Explanations
mentions of specific individuals, particularly "Jeff."
New Auto-Interp
Negative Logits
PyExc
-0.70
Chry
-0.66
jurado
-0.58
Schn
-0.58
Mure
-0.55
CloseOperation
-0.54
Erskine
-0.53
McCar
-0.52
Spicer
-0.52
Taj
-0.52
POSITIVE LOGITS
Jeff
1.31
Jeff
1.16
JEFF
1.09
jsp
1.06
jeff
1.05
jeff
1.00
Dave
0.98
Dave
0.94
JEFF
0.92
OP
0.87
Activations Density 0.058%