INDEX
Explanations
references to authorship.
The neuron activates on occurrences of the word “author” (e.g. in copyright or @author comment lines).
New Auto-Interp
Negative Logits
TPP
-0.07
sanitize
-0.06
ládání
-0.06
.;.;.;.;
-0.06
<header
-0.06
sın
-0.06
calendar
-0.06
_runs
-0.06
Reduced
-0.06
děl
-0.06
POSITIVE LOGITS
В
0.07
ическая
0.07
Tear
0.07
(KEY
0.07
gets
0.06
DD
0.06
entert
0.06
Observer
0.06
author
0.06
&T
0.06
Activations Density 0.000%