INDEX
Explanations
mentions of the name "Jeremy"
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
680
+0.15
0.7%
1937
+0.14
0.6%
1506
+0.13
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
981
+0.15
0.03
1335
+0.14
0.03
1506
+0.13
0.02
Negative Logits
arranging
-0.48
arbejds
-0.45
ellemző
-0.45
gorą
-0.45
Dill
-0.43
Normdatei
-0.43
Trix
-0.42
mulighed
-0.42
хви
-0.42
szczy
-0.41
POSITIVE LOGITS
Jeremy
1.37
Jeremy
1.30
JER
1.18
jeremy
0.98
JER
0.98
jer
0.97
alkoh
0.93
Jer
0.92
notor
0.85
Jer
0.83
Activations Density 0.154%