INDEX
Explanations
mentions of the name "Steven" and references to Steven Spielberg
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
101
+0.16
0.8%
966
+0.15
0.8%
50
+0.14
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
966
+0.16
0.02
1741
+0.15
0.01
1097
+0.14
0.03
Negative Logits
<bos>
-1.31
tròn
-0.54
map
-0.54
Tripp
-0.51
relax
-0.51
ガニック
-0.49
ൂ
-0.49
ുറ
-0.49
yık
-0.49
morph
-0.47
POSITIVE LOGITS
Steven
1.58
Steven
1.57
steven
1.42
STEVEN
1.25
steven
1.25
Stevenson
1.03
Stevens
1.02
Sinal
1.00
Lettre
0.95
Stevens
0.93
Activations Density 0.201%