INDEX
Explanations
mentions of the word "shore"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1937
+0.08
0.2%
197
+0.07
0.2%
554
+0.07
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1928
+0.08
0.02
485
+0.07
0.02
292
+0.07
0.02
Negative Logits
WriteLiteral
-0.79
int
-0.76
beforeEach
-0.70
def
-0.69
PutMapping
-0.69
ynb
-0.69
void
-0.69
///
-0.68
BufferException
-0.68
ngh
-0.67
POSITIVE LOGITS
shore
2.51
swarovski
2.17
milf
2.15
Shore
2.14
excru
2.14
hairc
2.13
maneu
2.12
Shore
2.11
disagre
2.05
indestru
2.05
Activations Density 0.175%