INDEX
Explanations
descriptions of being physically surrounded by something
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
2004
+0.13
0.4%
1222
+0.12
0.4%
597
+0.12
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2004
+0.13
0.03
1137
+0.12
0.02
597
+0.12
0.02
Negative Logits
};*/
-0.49
"$_
-0.47
""}
-0.46
Cár
-0.45
aluc
-0.45
secara
-0.45
eier
-0.44
sightly
-0.44
pegawai
-0.44
Ceux
-0.43
POSITIVE LOGITS
surround
1.17
surrounding
1.09
surrounds
1.07
Surround
1.06
surrounded
1.06
surroundings
0.94
AROUND
0.69
around
0.69
Around
0.65
around
0.63
Activations Density 0.092%