INDEX
Explanations
words related to mathematical concepts and calculations, specifically involving vectors and scalars
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
196
+0.14
0.6%
1392
+0.14
0.6%
1758
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
196
+0.14
0.02
1363
+0.14
0.02
1392
+0.13
0.02
Negative Logits
reconno
-1.31
gaily
-1.24
maneu
-1.20
reluct
-1.19
unspeak
-1.16
shenan
-1.15
tolerably
-1.14
intersper
-1.13
accla
-1.10
milf
-1.10
POSITIVE LOGITS
vector
1.43
vector
1.39
Vector
1.34
Vector
1.33
vectors
1.26
vectors
1.10
VECTOR
1.07
vec
0.98
vektor
0.97
vec
0.95
Activations Density 0.121%