INDEX
Explanations
mentions of the name "Charles"
New Auto-Interp
Negative Logits
WriteLiteral
-0.61
ktop
-0.60
-0.57
-0.55
Republic
-0.54
SPY
-0.53
umán
-0.52
Natalia
-0.52
theſe
-0.51
baijan
-0.51
POSITIVE LOGITS
Charles
1.62
Charles
1.51
CHARLES
1.23
charles
1.21
CHARLES
1.13
charles
1.02
Chronic
0.91
Chronic
0.90
chronic
0.84
Чар
0.80
Activations Density 0.072%