INDEX
Explanations
the concept of possession or belonging
New Auto-Interp
Head Attr Weights
0:0.06
1:0.08
2:0.08
3:0.08
4:0.10
5:0.07
6:0.07
7:0.11
8:0.07
9:0.05
10:0.09
11:0.10
Negative Logits
microscopic
-1.79
libel
-1.73
coil
-1.70
bullish
-1.65
neut
-1.61
untrue
-1.59
coils
-1.58
Frenchman
-1.57
eternity
-1.54
tubes
-1.52
POSITIVE LOGITS
oun
2.01
eret
1.92
inav
1.92
olen
1.82
rir
1.82
onomy
1.81
izo
1.80
udeb
1.79
cohol
1.79
inion
1.77
Activations Density 0.000%