INDEX
Explanations
instructions related to freezing and cooking food
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
198
+0.11
0.3%
468
+0.10
0.3%
876
+0.10
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
509
+0.11
0.07
284
+0.10
0.06
2044
+0.10
0.07
Negative Logits
„,
-1.29
Cfr
-1.26
thut
-1.26
fta
-1.21
aen
-1.19
emphat
-1.17
ftu
-1.16
?...
-1.15
Juf
-1.15
tew
-1.14
POSITIVE LOGITS
due
0.79
unless
0.78
enderror
0.76
when
0.74
during
0.68
too
0.67
or
0.67
if
0.63
unless
0.62
due
0.62
Activations Density 0.520%