INDEX
Explanations
references to individuals named David
New Auto-Interp
Negative Logits
šit
-0.16
ragen
-0.16
.timeScale
-0.15
referrer
-0.15
.tie
-0.15
ISP
-0.15
ypi
-0.15
avel
-0.15
yar
-0.15
BJECT
-0.14
POSITIVE LOGITS
son
0.22
SON
0.18
ic
0.18
Bowie
0.18
Ñģон
0.17
sons
0.17
Petra
0.17
enko
0.17
Letter
0.16
rint
0.16
Activations Density 0.018%