INDEX
Explanations
references to theft or illegal acquisition
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1145
+0.14
0.5%
331
+0.12
0.4%
1437
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1437
+0.14
0.03
1622
+0.12
0.02
1872
+0.12
0.03
Negative Logits
michelin
-0.93
chrysler
-0.89
hdi
-0.89
mitsubishi
-0.88
lidl
-0.87
lola
-0.87
fup
-0.85
peugeot
-0.84
guarante
-0.83
ibiza
-0.83
POSITIVE LOGITS
steal
1.29
stolen
1.24
steals
1.18
stole
1.16
stealing
1.14
theft
1.10
stolen
1.02
Steal
1.00
steal
0.95
thief
0.92
Activations Density 0.091%